國立虎尾科技大學 |

Disaster Resiliency in Cloud Networks.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Disaster Resiliency in Cloud Networks./
作者:	Ferdousi, Sifat.
面頁冊數:	1 online resource (155 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-09(E), Section: B.
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9780355969474

Disaster Resiliency in Cloud Networks.
Ferdousi, Sifat.

Disaster Resiliency in Cloud Networks. - 1 online resource (155 pages)

Source: Dissertation Abstracts International, Volume: 79-09(E), Section: B.

Thesis (Ph.D.)--University of California, Davis, 2018.

Includes bibliographical references

Recent occurrences of disasters and targeted attacks highlight the importance of disaster-resilient cloud network design. With increasing traffic volume in cloud networks and emerging bandwidth-hungry cloud services, failures due to disasters (both natural and human-made) may cause extensive data loss and service disruptions. In this dissertation, we explore novel proactive and reactive cloud network disaster-resiliency measures. We investigate how to combat disaster failures in cloud networks at different phases of the disaster. We propose strategies to i) prepare for disasters to safeguard data/content, ii) adapt to disasters to mitigate data loss, and iii) efficiently recover the network (ensure content reachability and service restoration) in case of inevitable disaster failures. The first part of the dissertation (Chapters 2 and 3) focuses on disaster preparedness and adaptability, and the second part (Chapters 4 and 5) focuses on post-disaster recovery.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355969474Subjects--Topical Terms:

596380
Electrical engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Disaster Resiliency in Cloud Networks.
LDR:04544ntm a2200337K 4500 001 914760
005 20180724121430.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780355969474
035 $a (MiAaPQ)AAI10689177
035 $a (MiAaPQ)ucdavis:17643
035 $a AAI10689177
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Ferdousi, Sifat. $3 1188099
245 1 0 $a Disaster Resiliency in Cloud Networks.
264 0 $c 2018
300 $a 1 online resource (155 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 79-09(E), Section: B.
500 $a Adviser: Biswanath Mukherjee.
502 $a Thesis (Ph.D.)--University of California, Davis, 2018.
504 $a Includes bibliographical references
520 $a Recent occurrences of disasters and targeted attacks highlight the importance of disaster-resilient cloud network design. With increasing traffic volume in cloud networks and emerging bandwidth-hungry cloud services, failures due to disasters (both natural and human-made) may cause extensive data loss and service disruptions. In this dissertation, we explore novel proactive and reactive cloud network disaster-resiliency measures. We investigate how to combat disaster failures in cloud networks at different phases of the disaster. We propose strategies to i) prepare for disasters to safeguard data/content, ii) adapt to disasters to mitigate data loss, and iii) efficiently recover the network (ensure content reachability and service restoration) in case of inevitable disaster failures. The first part of the dissertation (Chapters 2 and 3) focuses on disaster preparedness and adaptability, and the second part (Chapters 4 and 5) focuses on post-disaster recovery.
520 $a The main topics of the dissertation are the following: 1. We present novel techniques for disaster-aware datacenter placement and content management to prepare cloud networks against disasters. Using disaster failure probabilities and risk analysis, we estimate the risk in terms of expected content loss in the network based on importance of the contents. Our proposed schemes minimize risk through i) initial disaster-aware datacenter and content placement that avoids disaster-vulnerable or risky regions in the network, and ii) updated content placement (through replication) based on dynamic network and disaster conditions. 2. We propose a rapid data evacuation strategy to save critical data in a cloud network in response to an upcoming disaster alert. The network will be greatly constrained in terms of resources and time due to the upcoming alert, so, the goal is to evacuate as much critical data as possible and as quickly as possible (to meet a predicted deadline). Our evacuation strategy selects the least-delay paths through an anycast network model, and schedules critical and vulnerable contents for evacuation from potentially risky locations to safe locations within the evacuation deadline. 3. For an efficient post-disaster recovery scheme, we investigate joint progressive network and DC recovery in which network recovery and DC recovery are conducted in a coordinated manner. Our proposed joint progressive recovery scheme schedules the sequential repair of network nodes/links and DCs in subsequent stages with the objective to maximize content reachability to users based on importance of the contents. We also present a "resource-aware" joint progressive recovery algorithm, which considers availability of repair resources at each stage of the recovery process in scheduling repairs. 4. With the network evolution toward 5G, end-to-end application-centric virtual network slices are becoming realizable. In case of disasters, multiple physical network components, supporting the virtual network slices, may fail, causing extensive service disruptions. We investigate slice-aware service restoration in metro-access networks with specialized recovery trucks to provide backup services as "temporary relief". We propose a routing and deployment strategy for the recovery trucks to restore services in the network so as to minimize service downtime (penalty) of the disrupted network slices.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 596380
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Davis. $b Electrical and Computer Engineering. $3 1178925
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10689177 $z click for full text (PQDT)