HALO: Hop-by-Hop Adaptive Link-State Optimal Routing

Michael, Nithin; Tang, Ao

doi:10.1109/tnet.2014.2349905

Cited by 51 publications

(26 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here is an example showing a sequence of natural numbers: [5,15,15,5,35] The visualization of sequence is shown in Figure 4. Researchers add a number at the beginning of each line to show its order.…”

Section: Sequence and String Typementioning

confidence: 99%

Computer Science & Information Technology

2018

View full text Add to dashboard Cite

Section: Sequence and String Typementioning

confidence: 99%

Computer Science & Information Technology

2018

View full text Add to dashboard Cite

“…RepFlow [32] and RepNet [33] replicate each mouse flow to opportunistically use the less congested path, and reduce the overall flow completion time in DCNs. Inspired by the Minimum Delay Routing [34], HALO [35] studies load-sensitive adaptive routing and implements its solution in the router software. These solutions are aware of the overall congestion status of the DCN and react fast for local failures or congestions.…”

Section: ) Congestion-ware Load Balancing Schemesmentioning

confidence: 99%

A New Approach to Stochastic Scheduling in Data Center Networks

Yuan¹,

Huang²,

Xu³

et al. 2018

IJCNC

View full text Add to dashboard Cite

The Quality of Service (QoS) of scheduling between latency-sensitive small data flows (a.k.a. mice) and throughput-oriented large ones (a.k.a. elephants) has become ever challenging with the proliferation of cloud-based applications. In light of this mounting problem, this work proposes a novel flow control scheme, HOLMES (HOListic Mice-Elephants Stochastic), which offers a holistic view of global congestion awareness as well as a stochastic scheduler of mixed mice-elephants data flows in Data Center Networks (DCNs). Firstly, we theoretically prove the necessity for partitioning DCN paths into sub-networks using a stochastic model. Secondly, the HOLMES architecture is proposed, which adaptively partitions the available DCN paths into low-latency and high-throughput sub-networks via a global congestion-aware scheduling mechanism. Based on the stochastic power-of-two-choices policy, the HOLMES scheduling mechanism acquires only a subset of the global congestion information, while achieves close to optimal load balance on each end-to-end DCN path. We also formally prove the stability of HOLMES flow scheduling algorithm. Thirdly, extensive simulation validates the effectiveness and dependability of HOLMES with select DCN topologies. The proposal has been in test in an industrial production environment. An extensive survey of related work is also presented.

show abstract

“…Also we are aimed to reduce the congestion in the transmission along with maintaining QoS in terms of increasing lifetime of portable nodes. [1] The packet must be destined to the multipath destination by using shortest path algorithm. Our paper propose the different measures of quality of services and reduces the traffic overhead.…”

Section: Proposed Systemmentioning

confidence: 99%

“…Packet switching [1] compares with another principal networking model, circuit switching, a method which preallocates dedicated network bandwidth exactly for each communication session, each having a constant bit rate and delay between nodes. In cases of probable services, such as cellular communication services, circuit switching is described by a fee per unit of connection time, even when no data is transferred, when packet switching is cast by a fee per unit of information transmitted, such as characters, packets, or messages.…”

Section: Introductionmentioning

confidence: 99%

Multi-hop Adaptive Link State Optimal Routing in Wireless Ad hoc Network

2017

IJSR

View full text Add to dashboard Cite

Exploitation of HALO scheme to accomplish unique routing is recently known as a superior technique. All previous works improved routing on WSN, there is no strong improvement on QoS and for multidestination routing with less traffic overhead. The enhancement on routing QoS and multi-destination packet routing are addressed by using triplet model and link state algorithm in this project. By exploitation of the approach each node, for all diverse node, the algorithm separately and regularly renews the piece of traffic bound to that leaves on each of its outgoing paths. At each recapitulation, the updates are calculated by applying on the shortest path evaluations to every target which in turns discovered by the inconsiderable costs of the network's paths. That means the insignificant link costs are applied to encounter the shortest paths are in turn acquired from link-state updates that are flooded within the network after each recapitulation. This way of system is also versatile which means it naturally discovers the constant network transforms and captures judgments considering the different convenient means. However this has accomplished to exclude the trade-off between optimality and comfort of execution and routing yet it can function properly if we tried to decreases the acknowledgement overhead traffic. This paper project that there is a overcrowding issue due to acknowledgements which is to be decreases by practicing 2ACK system with triplet model and this will encouraged to decrease traffic and improve link employment for multi-destination routing keeping QoS also it maintains the transmission path log history for future communication.

show abstract

HALO: Hop-by-Hop Adaptive Link-State Optimal Routing

Cited by 51 publications

References 28 publications

Computer Science & Information Technology

Computer Science & Information Technology

A New Approach to Stochastic Scheduling in Data Center Networks

Multi-hop Adaptive Link State Optimal Routing in Wireless Ad hoc Network

Contact Info

Product

Resources

About