Abstract

Because mobile ad hoc networks have characteristics such as lack of center nodes, multi-hop routing and changeable topology, the existing checkpoint technologies for normal mobile networks cannot be applied well to mobile ad hoc networks. Considering the multi-frequency hierarchy structure of ad hoc networks, this paper proposes a hybrid checkpointing strategy which combines the techniques of synchronous checkpointing with asynchronous checkpointing, namely the checkpoints of mobile terminals in the same cluster remain synchronous, and the checkpoints in different clusters remain asynchronous. This strategy could not only avoid cascading rollback among the processes in the same cluster, but also avoid too many message transmissions among the processes in different clusters. What is more, it can reduce the communication delay. In order to assure the consistency of the global states, this paper discusses the correctness criteria of hybrid checkpointing, which includes the criteria of checkpoint taking, rollback recovery and indelibility. Based on the designed Intra-Cluster Checkpoint Dependence Graph and Inter-Cluster Checkpoint Dependence Graph, the elimination rules for different kinds of checkpoints are discussed, and the algorithms for the same cluster checkpoints, different cluster checkpoints, and rollback recovery are also given. Experimental results demonstrate the proposed hybrid checkpointing strategy is a preferable trade-off method, which not only synthetically takes all kinds of resource constraints of Ad hoc networks into account, but also outperforms the existing schemes in terms of the dependence to cluster heads, the recovery time compared to the pure synchronous, and the pure asynchronous checkpoint advantage.

Highlights

  • Average Checkpoint Time (ACT): average time for finishing the checkpointing procedure; Average Recovery Time (ART): average time for finishing the rollback recovery operation; Average Storage Size (ASS): average disk space that is occupied by the checkpoints of Multi-hops routing (MH); Average Additional Messages (AAM): average number of messages for checkpoints coordination and rollback recovery despite the normal communication messages; Average Cluster head Forwarded Messages (ACFM): average number of messages forwarded by the cluster head

  • The checkpoint frequency of a process is decided by the message threshold K in hybrid checkpointing protocol (HCP)

  • Because the storage overhead of checkpoints is much larger than the average storage overhead of message logs, so the storage overhead will reduce as K increases

Read more

Summary

Research Motive

As a new kind of network technology in the wireless communication field, the mobile ad hoc network, which doesn’t depend on fixed infrastructures, has been widely applied to different kinds of situations such as offices, industries and military, etc., bcause it can construct a multi-hops network with the existing network, and support wireless transmission of data, voices and images under bad environmental conditions by temporarily constructing a smart network. Mobile ad hoc networks have some limitations such as lack of support of fixed networks, limited resources and changeable topological structure. The processes are required to store their current states at a regular or unregularly period, so they just need to roll back to a specific checkpoint instead of the initial state when a failure occurs, to greatly reduce the recovery time [3,4]. MHs in different clusters needs to be transmitted by multiple intermediate nodes This will increase the number of wireless communication messages and communication delays for the checkpointing procedure. It is necessary to design new checkpoint technologies for coping with the upper challenges to improve the fault tolerance and reliability of mobile ad hoc networks

Related Works
Work and Organization of This Paper
Mobile Ad Hoc Network Topological Structure
Hybrid
An uncertain checkpoint is awireless
Problem of Hybrid Checkpointing Model to Be Solved
Correctness Criteria for a Hybrid Checkpointing Model
Checkpoint Taking Criteria
Checkpoint Rollback Criteria
Checkpoint Indelibility Criteria
Checkpoint Triggering Occasions
Reactive
Section 5.
Example of DC
Intra-Cluster Checkpoint Dependence Graph
Inter-Cluster
Rules and Strategies of Checkpiont Elimination
Elimination ofthe
By time the theclusters
If there is any edgethen which started by checkpoint
Algorithm for Checkpoints in the Same Cluster
Algorithm for Checkpoints in Different Clusters
Processing of Handoffs
Process States and Treatment
The Process Stays in the Rollback State
Update of Checkpoint Dependence Relation
The Process Stays the Checkpoint State
Update of Checkpoints Dependence Relation in Old Cluster
Update of Checkpoints Dependence Relation in New Cluster
Experiment Environment and Parameters
Experiment 1 Selection of K
Testthe ofACT
Experiment
12. Impact
Experiment 4 Test of ASS
Experiment 5 Test
16. Impact
17. Impact
Conclusions
Conclusions andof
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call