Shadow Computing: An energy-aware fault tolerant computing model

Mills, Bryan; Znati, Taieb; Melhem, Rami

doi:10.1109/iccnc.2014.6785308

Cited by 25 publications

(11 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address outsourcing security issues, initially, the cloud supplier should be reliable by giving trust and secure computing and data stockpiling; second, outsourced data and computation might be evident to clients as far as classification, honesty, and other security administrations. Likewise, outsourcing will possibly bring about security violation, because of the way that delicate data is out of the proprietor's control [2]. 2.…”

Section: Security Feature In Cloud Computingmentioning

confidence: 99%

“…Even though, there is no requirement of knowledge or expertise to control the infrastructure of clouds; it is abstract to the user. It is a service of an Internet with high scalability, quality of service, higher throughput and high computing power [2]. Cloud computing providers deploy common online business applications which are accessed from servers through web browser.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Data Confidentiality and Portability in Cloud Storage

Kaur

2018

ijarcs

View full text Add to dashboard Cite

In today's era, cloud computing becomes the hottest topic due to its ability to reduce the cost associated with computing. Cloud computing provides the on-demand services like storage, servers, resources etc. to the users without physically acquiring them and the payment is according to pay per use. Since cloud provides the storage, reduces the managing cost and time for an organization to the user but security and confidentiality become one of the biggest obstacles in front of us. The major problem with cloud environment is the number of the user is uploading their data on cloud storage so sometimes due to lack of security, there may be chances of loss of confidentiality. To overcome these obstacles a third party is required to prevent data, data encryption, and integrity and control unauthorized access to data storage to the cloud. Cloud portability becomes critical in the situation of loss of confidentiality. To optimize better results we will review some paper and find the better results to remove the security barriers.

show abstract

Section: Security Feature In Cloud Computingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Efficient Data Confidentiality and Portability in Cloud Storage

Kaur

2018

ijarcs

View full text Add to dashboard Cite

show abstract

“…Once an instance saves a checkpoint, the other instance can use this checkpoint immediately to "jump ahead" in its execution. A similar technique named shadow replication has been introduced in [12]. In this work, the authors consider a slow and a fast replica in order to both increase the reliability of the execution and reduce the associated energy consumption.…”

Section: Introductionmentioning

confidence: 99%

Optimal Checkpointing Period with Replicated Execution on Heterogeneous Platforms

Benoît

Cavelan

Fèvre

et al. 2017

Proceedings of the 2017 Workshop on Fault-Tolerance for HPC at Extreme Scale

View full text Add to dashboard Cite

In this paper, we design and analyze strategies to replicate the execution of an application on two di erent platforms subject to failures, using checkpointing on a shared stable storage. We derive the optimal pa ern size W for a periodic checkpointing strategy where both platforms concurrently try and executeW units of work before checkpointing. e rst platform that completes its pa ern takes a checkpoint, and the other platform interrupts its execution to synchronize from that checkpoint. We compare this strategy to a simpler on-failure checkpointing strategy, where a checkpoint is taken by one platform only whenever the other platform encounters a failure. We use rst or second-order approximations to compute overheads and optimal pa ern sizes, and show through extensive simulations that these models are very accurate. e simulations show the usefulness of a secondary platform to reduce execution time, even when the platforms have relatively di erent speeds: in average, over a wide range of scenarios, the overhead is reduced by 30%. e simulations also demonstrate that the periodic checkpointing strategy is globally more e cient, unless platform speeds are quite close.

show abstract

“…This model allows for combining SDC detection with shadow computing [36], where only the primary replica processes proceed at full speed and others can be operated at lower power. Slower replicas would provide eventual confirmation of results;…”

Section: Chapter 3 Designmentioning

confidence: 99%

“…Another body of work within resilience concentrates on management of the replica processes themselves. Shadow computing executes non-primary replica processes at slower speeds [36,12,13]. When the primary processes are successful, the replicas can be terminated early, saving power.…”

Section: Process Managementmentioning

confidence: 99%

Lazy Fault Detection for Redundant MPI

Ford¹

View full text Add to dashboard Cite

show abstract

Shadow Computing: An energy-aware fault tolerant computing model

Cited by 25 publications

References 6 publications

Efficient Data Confidentiality and Portability in Cloud Storage

Efficient Data Confidentiality and Portability in Cloud Storage

Optimal Checkpointing Period with Replicated Execution on Heterogeneous Platforms

Lazy Fault Detection for Redundant MPI

Contact Info

Product

Resources

About