Network failure–aware redundant virtual machine placement in a cloud data center

Zhou, Aoying; Wang, Shangguang; Hsu, Ching‐Hsien; Wong, Kok‐Seng

doi:10.1002/cpe.4290

Cited by 17 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The target of the online fault tolerance is to find an optimal service composition to replace the failed one and satisfy the functional and non-functional (QoS) constraints at the same time. In the existing studies, the problem can be abstracted as a 0-1 integer constrained multi-objective optimization problem, which is formulated in (14).…”

Section: ) Service Availabilitymentioning

confidence: 99%

A Two-Stage Fault Tolerance Method for Large-Scale Manufacturing Network

Peng

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Nowadays, networked manufacturing paradigm, such as cloud manufacturing, has brought new challenges for fault tolerance methods. Failures and errors of manufacturing services are unavoidable in the large-scale network. Appropriate fault tolerance methods need to be adopted to improve the reliability of the whole manufacturing network. Aiming at solving this problem, a two-stage fault tolerance method is, thus, proposed. In the off-line stage, a LeaderRank-based manufacturing nodes ranking (LNR) algorithm is put forward to rank the manufacturing services according to their significance in fault tolerance. Replication strategies are employed only for critical services to achieve the tradeoff between fault tolerance effect and fault tolerance loss. In the online stage, an A*-based heuristic alternative path searching (AHPS) algorithm is proposed to find suitable replacement schemes for composite services. The experimental results illustrate that the two-stage fault tolerance method can improve the reliability of large-scale manufacturing networks both effectively and efficiently.

show abstract

Section: ) Service Availabilitymentioning

confidence: 99%

A Two-Stage Fault Tolerance Method for Large-Scale Manufacturing Network

Peng

Wang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Until the process is complete, the routing of packets is performed based on outdated or missing entries, and many packets may be lost. Great efforts have been made to reduce the time required for a routing protocol to advertise information about network changes and recalculate the new set of shortest routes [14][15][16][17][18][19][20][21][22][23]. However, simply shortening the routing protocol timers to achieve faster network convergence is not recommended as this can lead to network destabilization by making the routing protocol too responsive [24][25][26].…”

Section: Introductionmentioning

confidence: 99%

Enhanced Bit Repair IP Fast Reroute Mechanism for Rapid Network Recovery

2021

View full text Add to dashboard Cite

The massive development of virtualized infrastructures, Internet of Things (IoT), and Wireless Sensor Network (WSN) in recent years has led to an increase in quality requirements for the management and reliability of underlay communication networks. Existing converged networks must therefore guarantee specific quantitative and qualitative parameters of different network communication services to meet customer requirements. However, the quality of the services operated is very negatively affected by an unpredictable failure of a communication link or a network node. In such situations, communication is typically interrupted for a period that is difficult to predict, and which can lead to significant financial losses and other negative effects. Internet Protocol Fast Reroute (IP FRR) technology was developed for these reasons. The paper presents the proposal of the new Enhanced Bit Repair (EB-REP) IP FRR mechanism, which offers significant improvements over its predecessor, the B-REP mechanism. The B-REP offers protection against a single failure and only for selected critical IP flows. The EB-REP provides advanced protection against multiple failures in a protected network domain and the protection can be provided for all network flows. The EB-REP calculates alternative paths in advance based on link metrics, but also allows the construction of alternative paths independently of them. The construction of alternative FRR paths uses a standardized tunneling approach via a unique field Bit-String. Thanks to these features, EB-REP is an advanced contribution to solving IP FRR-related problems, which enables the use of EB-REP in many network deployments, but especially in network solutions that require reliable data transmission.

show abstract

“…Regardless of these facts, however, computing a replacement path after the primary path has failed always incurs a possibly significant increase in network convergence time because the process begins only after the primary path has already become unusable. Many efforts have gone into shortening the time needed for a routing protocol to advertise a change in network connectivity and re-compute the new set of shortest paths [3][4][5][6][7][8] ; however, there is a fine line between rapid convergence and destabilization of the network by making a routing protocol respond too eagerly. [9][10][11] An important fact is that a given router at a particular place in a network topology only has a finite (and usually very small) set of possible failure scenarios relevant to network convergence.…”

Section: Introductionmentioning

confidence: 99%

The new Multicast Repair (M‐REP) IP fast reroute mechanism

Papán

Segeč

Palúch

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary The network convergence time may take hundreds of milliseconds or more. Since this repair performance may be unsatisfactory, IP fast reroute (IPFRR) approaches have been developed to decrease the network convergence time and minimize traffic loss. These IPFRR mechanisms are usually based on the proactive precomputation of a backup path before a failure occurs. Once a failure is detected, the router running IPFRR will immediately use this backup path in response to the failure, rather than computing a replacement path only after a failure has occurred. The computation of an alternative path in many IPFRR mechanisms requires that the computing node (router) knows the exact network topology. In this paper, we present a new IPFRR mechanism called the multicast repair (M‐REP) IPFRR mechanism, which provides an advanced fast reroute technique for Internet service providers‘ (ISP‘s) core networks. The M‐REP IPFRR mechanism is based on IP multicast and utilizes Protocol Independent Multicast – Dense Mode (PIM‐DM) with the modification of an internal reverse path forwarding (RPF) check. The M‐REP IPFRR mechanism does not depend on any particular routing protocol type (distance‐vector or link‐state) and requires less system resources because of its precomputation‐less character but still provides immediate reaction to failure.

show abstract

Network failure–aware redundant virtual machine placement in a cloud data center

Cited by 17 publications

References 29 publications

A Two-Stage Fault Tolerance Method for Large-Scale Manufacturing Network

A Two-Stage Fault Tolerance Method for Large-Scale Manufacturing Network

Enhanced Bit Repair IP Fast Reroute Mechanism for Rapid Network Recovery

The new Multicast Repair (M‐REP) IP fast reroute mechanism

Contact Info

Product

Resources

About