Measurement and Modeling of the Origins of Starvation in Congestion Controlled Mesh Networks

Shi, Jingpu; Gurewitz, Omer; Mancuso, Vincenzo; Camp, Joseph; Knightly, Edward W.

doi:10.1109/infocom.2008.224

Cited by 42 publications

(33 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Assume that both transmitters are in the first backoff stage, i.e., they choose a random backoff between 0-31 time slots. A collision at R 1 is inevitable as the two transmissions can be at most 32 time slots (640 μs for 802.11b) apart, while it takes upwards of 1, 500 μs to transmit a 1,500-byte Ethernet-friendly MTU and its subsequent link-level acknowledgement (ACK) using 802.11b physical layer parameters [3]. This collision only impacts S 1 's packet to R 1 .…”

Section: Starvation From Collisionsmentioning

confidence: 99%

“…However, these networks often exhibit poor-performance characteristics. Multihop flows experience unfairness, including starvation, when competing with nodes closer to the gateway [1][2][3]. This is primarily due to the inherent *Correspondence: kamjam@acm.org 1 CEMSE Division, KAUST, Thuwal, Saudi Arabia Full list of author information is available at the end of the article limitations of carrier sense multiple access with collision avoidance (CSMA/CA) media access control (MAC) protocol in a multihop environment, as well as its operational specifications in the IEEE 802.11 distributed coordination function (DCF) access mechanism.…”

Section: Introductionmentioning

confidence: 99%

“…Without any explicit rate feedback to data sources, this unfairness persists for the duration that the contending flows are active. Existing congestion control protocols such as transmission control protocol (TCP) fail to provide this rate feedback in CSMA/CA-based systems [1,3]. These problems remain inherent in DCF extensions such as enhanced distributed channel access (EDCA), which schedules elastic TCP streams using the 'Background' or 'Best Effort' class.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The efficacy of centralized flow rate control in 802.11-based wireless mesh networks

Jamshaid

Ward

Karsten

et al. 2013

J Wireless Com Network

View full text Add to dashboard Cite

Commodity WiFi-based wireless mesh networks (WMNs) can be used to provide last mile Internet access. These networks exhibit extreme unfairness with backlogged traffic sources. Current solutions propose distributed source-rate control algorithms requiring link-layer or transport-layer changes on all mesh nodes. This is often infeasible in large practical deployments. In wireline networks, router-assisted rate control techniques have been proposed for use alongside end-to-end mechanisms. We wish to evaluate the feasibility of establishing similar centralized control via gateways in WMNs. In this paper, we focus on the efficacy of this control rather than the specifics of the controller design mechanism. We answer the question: Given sources that react predictably to congestion notification, can we enforce a desired rate allocation through a single centralized controller? The answer is not obvious because flows experience varying contention levels, and transmissions are scheduled by a node using imperfect local knowledge. We find that common router-assisted flow control schemes used in wired networks fail in WMNs because they assume that (1) links are independent, and (2) router queue buildups are sufficient for detecting congestion. We show that non-work-conserving, rate-based centralized scheduling can effectively enforce rate allocation. It can achieve results comparable to source rate limiting, without requiring any modifications to mesh routers or client devices.

show abstract

Section: Starvation From Collisionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The efficacy of centralized flow rate control in 802.11-based wireless mesh networks

Jamshaid

Ward

Karsten

et al. 2013

J Wireless Com Network

View full text Add to dashboard Cite

show abstract

“…If the optional RTS/CTS handshake is disabled, then p → 1. If RTS/CTS is enabled, then p is typically much smaller, but still non-zero because RTS messages may collide [14]. Indeed, the transmission time of a control message (e.g., the RTS transmission time at the 1Mb/s basic rate is 352μs) is nonnegligible compared to the duration of a backoff slot (20μs).…”

Section: B Stealing Effectmentioning

confidence: 99%

Models of 802.11 multi-hop networks: Theoretical insights and experimental validation

Aziz

Durvy²,

Dousse³

et al. 2011

2011 Third International Conference on Communication Systems and Networks (COMSNETS 2011)

View full text Add to dashboard Cite

Abstract-Wireless Multi-Hop CSMA/CA Networks are challenging to analyze. On the one hand, their dynamics are complex and rather subtle effects may severely affect their performance. Yet, understanding these effects is critical to operate upper layer protocols, such as TCP/IP. On the other hand, their models tend to be very complex in order to reproduce all the features of the protocol. As a result, they do not convey much insight into the essential features.We review two models of 802.11 protocols, which are simple enough to first explain why a trade-off needs to be found between fairness and spatial reuse (throughput) in saturated wireless networks (where all nodes have packets to transmit to their neighbors); and then to explain why non-saturated networks (where only some nodes, the sources, have packets to transmit to their destinations in a multi-hop fashion) that are more than 3 hops longs suffer from instability. We confront both models either to realistic simulations in ns-2 or to experiments with a testbed deployed at EPFL. We find that the predictions of both models help us understand the performance of the 802.11 protocol, and provide hints about the changes that need to be brought to the protocol.

show abstract

“…The flows not only use the bandwidth all along its path, but also contend for the neighbor's bandwidths path. Such inter-flow intrusion effects bandwidth starvation for certain nodes as they encounter busy channels [9]. To overcome it, a routing metric helps routing protocols decide paths that stabilize the traffic load all along the flow path, and also minimize the inter-flow interference forced in the whole neighboring locale.…”

Section: Introductionmentioning

confidence: 99%

A Packet Priority Approach to Mitigate Starvation in Wireless Mesh Network with Multimedia Traffic

Potti¹,

Subramanyam²,

Prasad³

2013

IJCA

View full text Add to dashboard Cite

Wireless Mesh Networks (WMN) faces the inherent problem of increased end to end delay over a multiple hop wireless link. The delay becomes more obvious as the number of hops count between the source and destination increases. Experimental results have shown two hop neighbours face starvation when there are one hop nodes within the same gateway. In this paper, it is proposed to study the effect of starvation in WMN for multimedia traffic which are governed by the end to end delay and jitter for QOS. A novel packet priority technique, Dynamic Weighted Round Robin (DWRR) is proposed to reduce the effect of starvation for multi hop nodes. The proposed technique is implemented and compared with network without packet priority techniques. Results show that the proposed technique can be used to reduce starvation in WMN. General TermsWireless Mesh Network (WMN), End to end delay, Jitter

show abstract

Measurement and Modeling of the Origins of Starvation in Congestion Controlled Mesh Networks

Cited by 42 publications

References 17 publications

The efficacy of centralized flow rate control in 802.11-based wireless mesh networks

The efficacy of centralized flow rate control in 802.11-based wireless mesh networks

Models of 802.11 multi-hop networks: Theoretical insights and experimental validation

A Packet Priority Approach to Mitigate Starvation in Wireless Mesh Network with Multimedia Traffic

Contact Info

Product

Resources

About