Cross-layer optimisations

Architecture and Surveys

[Granelli 2007]

Fabrizio Granelli,
“The Cross-Layer Paradigm In Next Generation Internet: Open Issues & Future Perspectives;,
Globecom 2007 ResiliNets Keywords: Cross-layer, Future Internet

Transport Layer and TCP

[Krishnan-Sterbenz-Eddy-Partridge-Allman-2004]

Rajesh Krishnan, James P.G. Sterbenz, Wesley M. Eddy, Craig Partridge, and Mark Allman,
“Explicit Transport Error Notification (ETEN) for Error-Prone Wireless and Satellite Networks”,
Computer Networks, vol.46, #3, October 2004, pp. 343–362

ResiliNets Keywords: Cross-layer, end-to-end transport

Keywords: Explicit transport error notification (ETEN); Explicit loss notification (ELN); Explicit congestion notification (ECN); Wireless and satellite networks; TCP performance; Congestion; Corruption; Bit errors; Channel fades

Abstract: "Wireless and satellite networks often have non-negligible packet corruption rates that can significantly degrade TCP performance. This is due to TCP's assumption that every packet loss is an indication of network congestion (causing TCP to reduce the transmission rate). This problem has received much attention in the literature. In this paper, we take a broad look at the problem of enhancing TCP performance under corruption losses, and include a discussion of the key issues. The main contributions of this paper are: (i) a confirmation of previous studies that show the reduction of TCP performance in the face of corruption loss, and in addition a plausible upper bound achievable with perfect knowledge of the cause of loss, (ii) a classification of the potential mitigation space, and (iii) the introduction of a promising new mitigation that employs rich cumulative information from intermediate nodes in a path to form a better congestion response."

ARQ and FEC Interactions with TCP

[[Chockalingam-Zorzi-Tralli-1999] .]

A. Chockalingam, Michele Zorzi and Velio Tralli
“Wireless TCP Performance with Link Layer FEC/ARQ ”,
IEEE ICC'99, #2, 1999, pp. 1212–1216

ResiliNets Keywords: FEC/ARQ protocol; Cross-Layer;Bit Error Rate

Keywords:FEC/ARQ protocol; Cross-Layer;Bit Error Rate;

Abstract: "In this paper, we investigate the performance of TCP Tahoe and NewReno on wireless links with a FEC/ARQ protocol at the link layer. The effect of link layer (LL) parameters like the LL packet size, number of LL transmission attempts, and FEC code rate on the TCP throughput is evaluated. It is shown that the retransmissions at the link layer must persist long enough to outlast the average bad state duration of the Rayleigh fading process in order to achieve performance better than TCP without an ARQ at the link layer. It is further shown that with a suitable link layer in place, TCP Tahoe offers as high a throughput as offered by other enhanced versions like NewReno in the considered wireless environment."

[Dzmitry Kliazovich 2006]

Dzmitry Kliazovich,
“Cross-Layer Perfomance Optimization in Wireless Local Area Networks”,

ResiliNets Keywords: Cross-layer, end-to-end transport

Transport Layer and Segment Size Adaptation

[[Hyogon-Changhoon-Inhyne-2006] .]

Hyogon Kim, Changhoon Han, Inhye Kang
“Reducing TCP response time in face of wireless uplink losses ”,
Vehicular Technology Conference, 2001. VTC 2001 Fall, IEEE VTS 54th, 2001, vol.1 , pp. 262–266

ResiliNets Keywords: TCP; Adaptive Segmentation; link layer retransmissions ; Bit Error Rate

Keywords:FEC/ARQ protocol; Cross-Layer;Bit Error Rate;

Abstract:"We evaluate a TCP-level method, TCP segment size adaptation, to overcome the impact of wireless uplink losses. The performance improvement obtained can be as large as orders-of-magnitudes, and the required TCP sender code modification is limited to a few lines. The improvement can be further bolstered by combining the adaptation method with retransmission timeout (RTO) backoff containment."

[[Choi-Choi-Su-2005] .]

Jin-Hee Choi,Jin-Ghoo Choi,and Chuck Yoo1 Su
“Adapting TCP Segment Size in Cellular Networks”,
P. Lorenz and P. Dini (Eds.): ICN 2005, LNCS 3421,2005, pp. 258–265

ResiliNets Keywords: TCP performance,Segment Error Rate,Cellular Networks Keywords:TCP performance,Segment Error Rate,Cellular Networks

Abstract: "In cellular networks, a frame size is generally made small to reduce the impact of errors. Thus, a segment of transport layer is splitted into multiple frames before transmission. A problem is that the whole segment is lost when a frame of a segment is lost. So, the segment error rate tends to be high even though the cellular network provides relatively the low frame error rate, which drops TCP performance. However, the relation between the frame size, the segment size and the error rate has not been closely investigated. In this paper, we analyze the impact of the segment size on TCP performance in cellular networks and propose a scheme alleviating the performance drop of TCP. Our result shows that our scheme reduces the drop by 82%."

[[Lee-Yang-Su-2006] .]

Chen-Wei Lee,Chu-Sing Yang,Yih-Ching Su
“Adaptive UEP and packet size assignment for scalable video transmission over burst-error channels”,
EURASIP Journal on Applied Signal Processing, vol.2006, #1, January. 2006, pp. 256–256

ResiliNets Keywords: Cross-layer,frame adapt,optimal size,burst-error channel

Keywords:Packet Size; Burst-error channel;Bit Error Rate;

Abstract: "This work proposes an adaptive unequal error protection (UEP) and packet size assignment scheme for scalable video transmission over a burst-error channel. An analytic model is developed to evaluate the impact of channel bit error rate on the quality of streaming scalable video. A video transmission scheme, which combines the adaptive assignment of packet size with unequal error protection to increase the end-to-end video quality, is proposed. Several distinct scalable video transmission schemes over burst-error channel have been compared, and the simulation results reveal that the proposed transmission schemes can react to varying channel conditions with less and smoother quality degradation."

Cross Layer Optimization:Introduction

[[Lin-Shroff-Shrikant-2006] .]

Lin, X., Shroff, N.B., Srikant, R,
“A Tutorial on Cross-Layer Optimization in Wireless Networks”,
Selected Areas in Communications, IEEE Journal on, vol.24,no.8,August 2006, pp. 1452–1463

ResiliNets Keywords: Cross-layer, Wireless Networks,

Abstract: "This tutorial paper overviews recent developments in optimization-based approaches for resource allocation problems in wireless systems. We begin by overviewing important results in the area of opportunistic (channel-aware) scheduling for cellular (single-hop) networks, where easily implementable myopic policies are shown to optimize system performance. We then describe key lessons learned and the main obstacles in extending the work to general resource allocation problems for multihop wireless networks. Towards this end, we show that a clean-slate optimization-based approach to the multihop resource allocation problem naturally results in a “loosely coupled” cross-layer solution. That is, the algorithms obtained map to different layers [transport, network, and medium access control/physical (MAC/PHY)] of the protocol stack, and are coupled through a limited amount of information being passed back and forth. It turns out that the optimal scheduling component at the MAC layer is very complex, and thus needs simpler (potentially imperfect) distributed solutions. We demonstrate how to use imperfect scheduling in the cross-layer framework and describe recently developed distributed algorithms along these lines. We conclude by describing a set of open research problems."

[[Kawadia-Kumar-2005] .]

Kawadia, V.; Kumar, P.R.,
“A cautionary perspective on cross-layer design”,
Wireless Communications, IEEE, vol.12, no.1,Feb 2005, pp. 3–11

ResiliNets Keywords: Cross-layer,adaptive-rate,

Abstract: "Recently, in an effort to improve the performance of wireless networks, there has been increased interest in protocols that rely on interactions between different layers. However, such cross-layer design can run at cross purposes with sound and longer-term architectural principles, and lead to various negative consequences. This motivates us to step back and reexamine holistically the issue of cross-layer design and its architectural ramifications. We contend that a good architectural design leads to proliferation and longevity, and illustrate this with some historical examples. Even though the wireless medium is fundamentally different from the wired one, and can offer undreamt of modalities of cooperation, we show that the conventional layered architecture is a reasonable way to operate wireless networks, and is in fact optimal up to an order. However the temptation and perhaps even the need to optimize by incorporating cross-layer adaptation cannot be ignored, so we examine the issues involved. We show that unintended cross-layer interactions can have undesirable consequences on overall system performance. We illustrate them by certain cross-layer schemes loosely based on recent proposals. We attempt to distill a few general principles for cross-layer design. Moreover, unbridled cross-layer design can lead to spaghetti design, which can stifle further innovation and be difficult to upkeep. At a critical time when wireless networks may be on the cusp of massive proliferation, the architectural considerations may be paramount. We argue that it behooves us to exercise caution while engaging in cross-layer design.."

[Modiano-1999 .]

Eytan Modiano
“An adaptive algorithm for optimizing the packet size used in wireless ARQ protocols”,
Wireless Networks Springer, vol.5, #4, July. 1999, pp. 279–286

ResiliNets Keywords: Cross-layer,frame adapt,optimal size

Keywords: Optimal Packet Size; Efficiency of a protocol;Bit Error Rate;

Abstract: "We develop an algorithm that allows an ARQ protocol to dynamically optimize the packet size based on estimates of the channel bitdasherrordashrate. Our algorithm is particularly useful for wireless and satellite channels where the bitdasherrordashrates tend to be relatively high and time variable. Our algorithm uses the acknowledgment history to make estimates of the channel bitdasherrordashrate, based on which the optimal packet size can be chosen. We develop a Markov chain model for the analysis of the system, under static channel conditions, and show that the algorithm can achieve close to optimal performance using a history of just 10,000 bits. We also use the Gilbert–Elliott twodashstate Markov channel to model dynamic channel conditions. We show, through simulation, that the algorithm performs well even under rapidly changing channel conditions. Finally, we discuss a maximum likelihood approach for choosing the packet size, which performs almost optimally but is much easier to implement."

[[Wang-Horan-Chandrasekaran-2006] (doi) .]

Ruhai Wang, Stephen Horan, Rama Chandrasekaran Su
“An experimental investigation of cross-layer optimal packet size in space Internet”,
International Journal of Satellite Communications and Networking, vol.24, #6,2006, pp. 561–577

ResiliNets Keywords: Cross-layer,frame adapt,optimal size,bit error rate,space Internet

Keywords:Packet Size;Bit Error Rate;

Abstract: "Studies of optimal packet size determination in space communication can be found in the literature. However, they are done in an analytical manner. In this paper, we present an experimental study of the cross-layer optimal packet size for a Transmission Control Protocol (TCP) Internet Protocol (IP) enhancement, Space Communication Protocol Standards (SCPS), using a personal computer (PC)-based testbed. We study the optimal packet size at the medium access control (MAC) layer considering the cross-layer interactions at the physical layer. We investigate how the cross-layer MAC packet size needs to be adjusted for optimal throughput performance based on the feedback of the bit-error rate (BER), space-link delay and symmetric/asymmetric channel-rate configurations at the physical channel, and find the cross-layer optimal packet size for the maximum throughput over the space-Internet channels. We find that the default TCP/IP packet size of 1500 bytes for the terrestrial Internet should be chosen as the cross-layer MAC packet size for optimal throughput performance over space channels with round-trip time (RTT) around 250 ms and BER⩽10-6. As the channel BER at the physical layer increases, the optimal MAC packet size should be reduced to around 1000 bytes. We also find that it is more significant to have an optimal packet size for asymmetric channel than symmetric channel but the optimal packet size remains the same at a given BER for both channel ratios in our experiment. To our knowledge, this is the first paper to investigate the cross-layer optimal MAC packet size over space-Internet channel in the proposed approach. Copyright © 2006 John Wiley & Sons, Ltd."

[[Bakin-Joa-McAuley-2000] .]

D.S.Bakin,M.Joa-Ng,A.J.McAuley
“Quantifying TCP performance improvements in noisy environmentsusing protocol boosters”,
Computers and Communications, 2000. Proceedings. ISCC 2000. Fifth IEEE Symposium, pp. 92–97

ResiliNets Keywords: TCP Performance,Protocol booster;

Keywords: Cross-layer,TCP Performance,Protocol booster;

Abstract: "This paper describes a robust method of improving TCP performance for terrestrial and satellite wireless networks without modification to TCP or change in its semantics. Tools to transparently improve performance have been around for many years and many work even when the TCP header information is encrypted (e.g., IPSEC) or TCP acknowledgments do not go through the reverse path. Little work has been done; however, to quantiy how beneficial these techniques are. Using protocol boosters we show that reducing the packet size is critical as bit error rates get worse than 10-5. We also show that over two orders of magnitude improvement in throughput can be achieved by adding redundant FEC packets, with well-chosen parameters for the number of data (k) and parity (h) packets in a block, and a small maximum encode time (t). It is important to note that we are looking strictly at enhancement techniques that do not require modifications at the end hosts as this can be a difficult task for the typical end user."

[[Hamadani-Rakocevic-2006] .]

Eshan Hamadani, Veselin Rakocevic,
"A cross layer Analysis of TCP instability in Multihop Ad hoc Networks",
European Wireless Conference, April 2007,

ResiliNets Keywords: Cross-layer, end-to-end transport, TCP

Abstract: "It is well-known that due to the nature of some ad hoc network applications (e.g. emergency operation,battlefield communication), TCP instability can have a devastating impact on the Quality of Service requirements. As we will show in this paper, TCP instability is truly a cross layer problem which needs to be addressed by considering the interaction of multiple layers with each other. We first divide the TCP instability problem into intra-flow and inter-flow instability and then propose a set of simple but effective solutions and show through extensive simulations the improvements achieved using the proposed algorithms."

[[Devetsikiotis-Kliazovich-Granelli-2007] [1]]

Michael Devetsikiotis.,Dzmitry Kliazovich,Fabrizio Granelli
“Formal Methods in Cross-Layer Modeling and Optimization of Wireless Networks:State of the Art and Future Directions”

=== [[Fu-Zerfos-Luo-Lu-Zhang-Gerla-2003] .]===

Fu, Z.; Zerfos, P.; Luo, H.; Lu, S.; Zhang, L.; Gerla, M,
“The impact of multihop wireless channel on TCP throughput and loss”,
INFOCOM 2003,IEEE Computer and Communications Societies. IEEE, vol.3, March 2003, pp. 1744–1753

ResiliNets Keywords: Cross-layer,Multihop,TCP

Abstract: "This paper studies TCP performance over multihop wireless networks that use the IEEE 802.11 protocol as the access method. Our analysis and simulations show that, given a specific network topology and flow patterns, there exists a TCP window size W*, at which TCP achieves best throughput via improved spatial channel reuse. However, TCP does not operate around W*, and typically grows its average window size much larger; this leads to decreased throughput and increased packet loss. The TCP throughput reduction can be explained by its loss behavior. Our results show that network overload is mainly signified by wireless link contention in multihop wireless networks. As long as the buffer size at each node is reasonably large (say, larger than 10 packets), buffer overflow-induced packet loss is rare and packet drops due to link-layer contention dominate. Link-layer drops offer the first sign for network overload. We further show that multihop wireless links collectively exhibit graceful drop behavior: as the offered load increases, the link contention drop probability also increases, but saturates eventually. In general, the link drop probability is insufficient to stabilize the average TCP window size around W*. Consequently, TCP suffers from reduced throughput due to reduced spatial reuse. We further propose two techniques, link RED and adaptive pacing, through which we are able to improve TCP throughput by 5% to 30% in various simulated topologies. Some simulation results are also validated by real hardware experiments."

Cross Layer and TCP

[Hamadani-Rakocevic-2008]

Ehsan Hamadani and Veselin Rakocevic,
“A Cross Layer Approach to Address TCP Intra-flow Instability in Multihop”,
Journal of Internet Engineering, vol.2, #1, 2008

ResiliNets Keywords: Cross-layer, TCP

Keywords: Inra-flow Instability; Inter-flow Instability; wireless 802.11; TCP performance; Congestion; OPTNET;

Abstract: "Incorporating the concept of TCP end-to-end congestion control for wireless networks is one of the primary concerns in designing ad hoc networks since TCP was primarily designed and optimized based on the assumptions for wired networks. In this study, our interest lies on tackling the TCP instability and in particular intra-flow instability problem since due to the nature of applications in multihop ad hoc networks, connection instability or starvation even for a short period of time can have a negative impact on the Quality of Service and may not be acceptable for the end user. Through a detailed analysis, it will be shown that the main causes of TCP intra-flow instability lies in overloading the network by sending more packets than the capacity of the channel. Based on this, the paper proposes a novel cross layer solution called TCP Contention Control that dynamically adjusts the amount of outstanding data in the network based on the level of contention experienced by packets as well as the throughput achieved by connections. The simulation results show TCP Contention Control can drastically improve TCP stability over 802.11 multihop ad hoc networks."

[Nahm-Helmy-Kuo-2008]

Kitae Nahm, Ahmed Helmy And C.C Jay Kuo
“TCP over Multihop 802.11 Networks: Issues And Performance Evaluation”,
Proceedings of the 6th ACM international symposium on Mobile ad hoc networking and computing, May 2005, pp. 277–287

ResiliNets Keywords: Cross-layer; Interaction between TCP and Routing; On-Demand Routing protocol; Congestion Control

Keywords: TCP performance; Multihop Wireless 802.11; FeW TCP;

Abstract: "Analyzing TCP operation over 802.11 multihop ad hoc networks involves a cross-layer study. In this work, we investigate the effect of congestion and MAC contention on the interaction between TCP and on-demand ad hoc routing protocol in the 802.11 ad hoc networks. Our study reveals several problems stemming from lack of coordination and sharing in such networks. It is observed that TCP induces the over-reaction of routing protocol and hurts the quality of end-to-end connection. So, one of the critical sources of lowering TCP throughput lies in the TCP window mechanism itself. To fix this problem, we propose a fractional window increment (FeW) scheme for TCP to prevent the over-reaction of the on-demand routing protocol by limiting TCP's aggressiveness. The proposed scheme is applicable to a wide range of transport protocols using the basic TCP mechanism, and the protocol behavior is analytically tractable. Our simulation results demonstrate that the proposed scheme can dramatically improve TCP performance and network stability in a variety of 802.11 multihop networks. For example, in some chain-like topologies, the proposed scheme outperforms basic TCP by over 90%, and recent related variants of TCP (ADTCP, LRED) by over 70%."

[Xiao-Shan-Ren-2005]

yongkang Xiao, xiuming Shan And Yong Ren
“Cross-Layer Design Improves TCP Performance in Multihop Ad Hoc Networks”,
IEICE Trans Commun (Inst Electron Inf Commun Eng), vol.E88-B, #8, August 2005, pp. 3375-3382

ResiliNets Keywords: Cross-layer; A-TCP; RTS retry count; Window Size; Congestion Control

Keywords: multihop ad hoc networks; IEEE 802.11 MAC protocol; TCP; congestion control mechanism; cross-layer design;

Abstract: "TCP performance in the IEEE 802.11-based multihop ad hoc networks is extremely poor, because the congestion control mechanism of TCP cannot effectively deal with the problem of packet drops caused by mobility and shared channel contention among wireless nodes. In this paper, we present a cross-layer method, which adaptively adjusts the TCP maximum window size according to the number of RTS (Request To Send) retry counts of the MAC layer at the TCP sender, to control the number of TCP packets in the network and thus decrease the channel contention. Our simulation results show that this method can remarkably improve TCP throughput and its stability"

[Kliazovich-Granelli-2005]

Dzmitry Kliazovich And fabrizio Granelli
“Cross-Layer Congestion Control in Ad hoc Wireless Netorks”,
IEICE Trans Commun (Inst Electron Inf Commun Eng), vol.E88-B, #8, August 2005, pp. 3375-3382

ResiliNets Keywords: Cross-layer;

Keywords: Congestion control; TCP-over-wireless; Multi-hop wireless networks

Abstract: "The paper presents the problem of performance degradation of transport layer protocols due to congestion of wireless local area networks. Following the analysis of available solutions to this problem, a cross-layer congestion avoidance scheme (C3TCP) is presented, able to obtain higher performance by gathering capacity information such as bandwidth and delay at the link layer. The method requires the introduction of an additional module within the protocol stack of the mobile node, able to adjust the outgoing data stream based on capacity measurements. Moreover, a proposal to provide optional field support to existing IEEE 802.11 protocol, in order to support the presented congestion control solution as well as many other similar approaches, is presented. Achieved results underline good agreement with design considerations and high utilization of the available resources."

[Raisinghani-Singh-Iyer-2002]

V. Raisinghani, A. Singh and S. Iyer
“Improving TCP Performance over Mobile Wireless Environments Using Cross Layer Feedback”,
IEEE International Conference on Personal Wireless Communications, 2002, pp. 81-85

ResiliNets Keywords: Cross-layer; User Feedback; Application Priority; Receiver Window Control RWC;

Abstract: "The transmission control protocol (TCP) is known to suffer from performance degradation in mobile wireless environments. This is because such environments are prone to packet losses due to high bit error rates and mobility induced disconnections. TCP interprets packet losses as an indication of congestion and inappropriately invokes congestion control mechanisms, which leads to degraded performance. We show how cross-layer feedback, i.e. information from layers above and below, may be used to improve TCP performance over wireless networks. To illustrate the power of cross layer feedback, we present two novel mechanisms. We incorporate user feedback into the protocol stack by which the TCP throughput of a desired set of applications running on the mobile host can be dynamically controlled. We propose an approach to use the lower layer connection and disconnection information, for improving TCP performance. Both these mechanisms entail minimal modification to the mobile host and no modifications to the sender or other network entities. We have implemented both these mechanisms in ns-2 and the simulation results demonstrate the effectiveness of cross layer feedback."

[Fu-Zerfos-Luo-Lu-Zhang-Gerla-2003]

Fu, Z.; Zerfos, P.; Luo, H.; Lu, S.; Zhang, L.; Gerla, M.
“The Impact of Multihop Wireless Channel on TCP Throughput and Loss”,
INFOCOM 2003. Twenty-Second Annual Joint Conference of the IEEE Computer and Communications Societies. IEEE, 2003, Vol. 3, pp. 1744- 1753

ResiliNets Keywords: Cross-layer; User Feedback; Application Priority; Receiver Window Control RWC;

Abstract: "This paper studies TCP performance over multihop wireless networks that use the IEEE 802.11 protocol as the access method. Our analysis and simulations show that, given a specific network topology and flow patterns, there exists a TCP window size W*, at which TCP achieves best throughput via improved spatial channel reuse. However, TCP does not operate around W*, and typically grows its average window size much larger; this leads to decreased throughput and increased packet loss. The TCP throughput reduction can be explained by its loss behavior. Our results show that network overload is mainly signified by wireless link contention in multihop wireless networks. As long as the buffer size at each node is reasonably large (say, larger than 10 packets), buffer overflow-induced packet loss is rare and packet drops due to link-layer contention dominate. Link-layer drops offer the first sign for network overload. We further show that multihop wireless links collectively exhibit graceful drop behavior: as the offered load increases, the link contention drop probability also increases, but saturates eventually. In general, the link drop probability is insufficient to stabilize the average TCP window size around W*. Consequently, TCP suffers from reduced throughput due to reduced spatial reuse. We further propose two techniques, link RED and adaptive pacing, through which we are able to improve TCP throughput by 5% to 30% in various simulated topologies. Some simulation results are also validated by real hardware experiments."

[Yu-2004]

Xin Yu
“Improving TCP Performance over Mobile Ah Hoc Networks by Exploiting Cross-layer Infromation Awareness”,
Proceedings of the 10th annual international conference on Mobile computing and networking, 2004, pp. 231 - 244

ResiliNets Keywords: Cross-layer; TCP Timeouts; Mobility; EPLN and BEAD; Cached Routes; Freeze Timer; Route restoration

Abstract: "TCP performance degrades significantly in mobile ad hoc networks because most of packet losses occur as a result of route failures. Prior work proposed to provide link failure feedback to TCP so that TCP can avoid responding to route failures as if congestion had occurred. However, after a link failure is detected, several packets will be dropped from the network interface queue; TCP will time out because of these losses. It will also time out for ACK losses caused by route failures. In this paper, we propose to make routing protocols aware of lost data packets and ACKs and help reduce TCP timeouts for mobility-induced losses. Toward this end, we present two mechanisms: early packet loss notification (EPLN) and best-effort ACK delivery (BEAD). EPLN seeks to notify TCP senders about lost data packets. For lost ACKs, BEAD attempts to retransmit ACKs at either intermediate nodes or TCP receivers. Both mechanisms extensively use cached routes, without initiating route discoveries at any intermediate node. We evaluate TCP-ELFN enhanced with the two mechanisms using two caching strategies for DSR, path caches and a distributed cache update algorithm proposed in our prior work. We show that TCP-ELFN with EPLN and BEAD significantly outperforms TCP-ELFN under both caching strategies. We conclude that cross-layer information awareness is key to making TCP efficient in the presence of mobility."

MULTIPATH

[Wischik-Raiciu-Greenhalgh-Handley-2011 (doi) .]

Damon Wischik, Costin Raiciu, Adam Greenhalgh and Mark Handley
“Design, implementation and evaluation of congestion control for multipath TCP”
Proceedings of the 8th USENIX conference on Networked systems design and implementation,
Boston, MA, March 2011, pp. 8–8

ResiliNets Keywords: Multipath, Implementation

Keywords:

Abstract: "Multipath TCP, as proposed by the IETF working group mptcp, allows a single data stream to be split across multiple paths. This has obvious benefits for reliability, and it can also lead to more efficient use of networked resources. We describe the design of a multipath congestion control algorithm, we implement it in Linux, and we evaluate it for multihomed servers, data centers and mobile clients. We show that some 'obvious' solutions for multipath congestion control can be harmful, but that our algorithm improves throughput and fairness compared to single-path TCP. Our algorithmis a drop-in replacement for TCP, and we believe it is safe to deploy."

Notes:

Bibliographic Entries

[Nacher-Carlos-Calafate-Manzoni-2007]

Marga Nacher; Carlos T. Calafate, Juan-Carlos Cano, Pietro Manzoni
“Comparing tcp and udp performance in manets using multipath enhanced versions of dsr and dymo”,
International Workshop on Modeling Analysis and Simulation of Wireless and Mobile Systems, 2007, Vol. 3, pp. 39-45

ResiliNets Keywords: Multipath; Performance; TCP; UDP; MANETS ; DSR ;DYMO; ns-2

Abstract: "This paper studies TCP performance over multihop wireless networks that use the IEEE 802.11 protocol as the access method. Our analysis and simulations show that, given a specific network topology and flow patterns, there exists a TCP window size W*, at which TCP achieves best throughput via improved spatial channel reuse. However, TCP does not operate around W*, and typically grows its average window size much larger; this leads to decreased throughput and increased packet loss. The TCP throughput reduction can be explained by its loss behavior. Our results show that network overload is mainly signified by wireless link contention in multihop wireless networks. As long as the buffer size at each node is reasonably large (say, larger than 10 packets), buffer overflow-induced packet loss is rare and packet drops due to link-layer contention dominate. Link-layer drops offer the first sign for network overload. We further show that multihop wireless links collectively exhibit graceful drop behavior: as the offered load increases, the link contention drop probability also increases, but saturates eventually. In general, the link drop probability is insufficient to stabilize the average TCP window size around W*. Consequently, TCP suffers from reduced throughput due to reduced spatial reuse. We further propose two techniques, link RED and adaptive pacing, through which we are able to improve TCP throughput by 5% to 30% in various simulated topologies. Some simulation results are also validated by real hardware experiments."

[Xu-Gerla-Lim-2003]

Kaixin Xu; Mario Gerla; Haejung Lim
“Tcp performance over multipath routing in mobile ad hoc networks”

ResiliNets Keywords: Multipath; TCP performance; ns-2; multipath routing, backup path routing

Abstract: "In this paper, we investigate TCP performance over a multipath routing protocol. Multipath routing can improve the path availability in mobile environment. Thus, it has a great potential to improve TCP performance in ad hoc networks under mobility. Previous research on multipath routing mostly used UDP traffic for performance evaluation. When TCP is used, we find that most times, using multiple paths simultaneously may actually degrade TCP performance. This is partly due to frequent out-of-order packet delivery via different paths. We then test another multipath routing strategy called backup path routing. Under the backup path routing scheme, TCP is able to gain improvements against mobility. We then further study related issues of backup path routing which can affect TCP performance. Some important discoveries are reported in the paper and simulation results show that by careful selection of the multipath routing strategies, we can improve TCP performance by more than 30% even under very high mobility."

[Gerla-Chen-Xu-2004]

Mario Gerla; Kaixin Xu. , Jiwei Chen
“Multipath TCP in Lossy Wireless Environment”,
IFIP Third Annual Mediterranean Ad Hoc Networking Workshop (Med-Hoc-Net 04), May 2004

ResiliNets Keywords: Multipath; M-TCP; MANETS ; DSR ; ns-2

Abstract: "Random loss in wireless ad hoc nets derives from two main causes: lossy wireless channels and node mobility. Breakage and loss can significantly degrade the performance of network protocols, especially TCP. Recently, several schemes have been proposed to protect TCP from mobility induced link breaks by freezing TCP state when a link break is detected. TCP freeze however does not help with high channel loss due to random interference. Multipath solutions had been attempted to protect TCP from mobility, but with no success. This paper addresses lossy channels. The authors repropose multipath routing to enhance TCP performance in lossy environment with heavy interference."

[Kultida-Hitoshi-2004]

Rojviboonnchai Kultida; Aida Hitoshi
“An evaluation of multi-path Transmission Control Protocol (M/TCP) with robust acknowledgement schemes”,
IEICE transactions on communications, 2004, vol 8, pages 2699-2707

ResiliNets Keywords: Multipath; M/TCP; ns-2; High PER, immediate ACK vs Robust ACK on reverse path

Abstract: "We propose a new end-to-end transport protocol called Multi-path Transmission Control Protocol (M/TCP) and its two robust acknowledgement (ACK) schemes. Our protocol is designed as an alternative TCP option to improve reliability and performance of the Internet. The M/TCP sender simultaneously transmits data via multiple controlled paths to the receiver. Our protocol requires no modification in IP layer. Two M/TCP endpoints establish multiple paths between them by subscribing to multiple ISPs. The two robust ACK schemes proposed in this paper aim at improving M/TCP performance over the Internet with high packet loss in ACK channels. Performances between our protocol and TCP Reno are compared in terms of throughput and fairness by using ns2 simulator. Simulation results indicate that M/TCP achieves higher throughput than TCP Reno in situation of random drop and burst traffic with small buffer size. When there is network congestion on reverse path, M/TCP with the proposed robust ACK schemes performs better than M/TCP with the conventional immediate ACK scheme"

[Lee-Gerla-2001]

Sung-Ju Lee; Mario Gerla
“Split Multipath Routing with Maximally Disjoint Paths in Ad hoc Networks”,
In Proceedings of the IEEE ICC, 2001, June, pages 3201-3205

ResiliNets Keywords: Multipath; ns-2; Routing, New Split Multipath Routing protocol - SMR

Abstract: "In recent years, routing has been the most focused area in adhoc networks research. On-demand routing in particular, is widely developed in bandwidth constrained mobile wireless ad hoc networks because of its effectiveness and efficiency. Most proposed on-demand routing protocols however, build and rely on single route for each data session. Whenever there is a link disconnection on the active route, the routing protocol must perform a route recovery process. In QoS routing for wired networks, multiple path routing is popularly used. Multiple routes are however, constructed using link-state or distance vector algorithms which are not well-suited for ad hoc networks. We propose an on-demand routing scheme called Split Multipath Routing (SMR) that establishes and utilizes multiple routes of maximally disjoint paths. Providing multiple routes helps minimizing route recovery process and control message overhead. Our protocol uses a per-packet allocation scheme to distribute data packets into multiple paths of active sessions. This traffic distribution efficiently utilizes available network resources and prevents nodes of the route from being congested in heavily loaded traffic situations. We evaluate the performance of our scheme using extensive simulation."

[Marina-Das-2001]

Mahesh K. Marina; Samir R. Das
“On-demand multipath distance vector routing in ad hoc networks”,
Proceedings of IEEE International Conference on Network Protocols, Nov 2001

ResiliNets Keywords: Multipath; ns-2; Routing, New DVR Protocol

Abstract: "We develop an on-demand, multipath distance vector protocol for mobile ad hoc networks. Specifically, we propose multipath extensions to a well-studied single path routing protocol known as Ad hoc On-demand Distance Vector (AODV). The resulting protocol is referred to as Ad hoc Ondemand Multipath Distance Vector (AOMDV). The protocol computes multiple loop-free and link-disjoint paths. Loopfreedom is guaranteed by using a notion of “advertised hopcount. ” Link-disjointness of multiple paths is achieved by using a particular property of flooding. Performance comparison of AOMDV with AODV using ns-2 simulations shows that AOMDV is able to achieve a remarkable improvement in the end-to-end delay — often more than a factor of two, and is also able to reduce routing overheads by about 20%."