We believe many interesting questions are left open as a follow up of this work. We give few examples of interesting research problems in the field of algorithmic design, and system implementation perspectives.
Mechanism Design: different utility functions can be used to design several em- bedding mechanisms, in which InPs and SP may cooperate or compete to achieve a common or a selfish embedding goal. An example of research problem would be to analyze and evaluate the performance of a distributed embedding protocol with (selfish) bidders, trying to win multiple slices in a single resource embedding round, modeling the scheme as an auction. Auction-based resource allocation schemes with- out currency have been floated before, as described in our related work chapter; we believe however that it is worth investigating the auction theory literature to pro- vide, e.g., incentive compatible auction and pricing mechanisms, in which physical nodes could maximize their profit and at the same time have incentives to bid their truthful value on each virtual resource.
System Implementation: designing and implementing a platform for scalable, isolated and reproducible distributed system experiments is still an open question, although the GENI community has made significant progress. We believe that an in- teresting research problem that would leverage our prototype implementation could be to provide a GENI “reproduce experiment” button, in which the same virtual network application is run on top of different physical resources.
Formal Verification of Protocols: we believe that an interesting research di- rection would also be to use formal method tools such as Alloy [Dan13] or Is- abelle [WW07], to show correctness of our consensus-based embedding mechanism.
CADE Synchronous Agreement Rules
In this appendix we report the conflict resolution rules used in the agreement phase of the synchronous cade protocol. This rules were inspired by the Consensus-based Decentralized Auction (CBBA) algorithm used for decentralized robot task alloca- tion [CBH09].
As defined in Chapter 4, a virtual network is denoted by the graph H = (VH, EH)
and a physical network by G = (VG, EG), where V is a set of (physical or virtual)
nodes, and E the set of (physical or virtual) edges. bi ∈ R |VH|
+ is the a vector of
utility values. Each entry bij ∈ bi is a positive real number representing the highest
utility value known so far on virtual node j ∈ VH. ai ∈ V |VH|
G is the winner vector
—a vector containing the latest information on the current assignment of all virtual nodes, for a distributed auction winner determination. aij ∈ ai is contains the
identity of the winner of virtual node j, as currently known from physical node i. si ∈ R
|VG|
+ is the a vector of time stamps of the last information update from each of
the other physical nodes i.e., the message reception time. There are three possible action when a physical node i receives a vote message from a sender physical node k: (i) update, where both the utility vector and the allocation vector are updated according to the sender information; (ii) reset, where the utility value is set to zero,
k thinks akj is i thinks aij is Receiver’s action (default leave) k i if bkj> bij → update k update m /∈ {i, k} if skm> sim or bkj> bij→ update none update i i leave k reset m /∈ {i, k} if skm> sim→ reset none leave m /∈ {i, k} i if skm> sim and bkj> bij→ update k skm> sim→ update else → reset n /∈ {i, k, m} if skm> sim and skn> sin→ update if skm> sim and bkj> bij→ update if skn> sinand sim> skm→ reset none if skm> sim→ update none i leave k update m /∈ {i, k} if skm> sim→ update none leave
Table A.1: Rules table for cade synchronous conflict resolution. The sender physical node is denoted with k, and the receiver physical node with i. The time vector s represents the time stamp of the last information update from each of the other agents.
and the allocation vector to null, and (iii) leave, where both the utility vector and the allocation vector are left unchanged by the receiver physical node.
VINEA Asynchronous
Agreement Rules
In this appendix we report the conflict resolution rules used in the vinea asynchronous implementation of the cade protocol.
The allocation vector a and the utility vectors b are defined in (Chapter 4 and in) Appendix A. The time stamp vector ti ∈ R
|VH|
+ is a vector of time stamps where
each entry tij ∈ ti is a positive real number representing the forging time of the bid
on virtual node j as currently known from physical node i. This vector is necessary for an asynchronous conflict resolution.
k thinks akj is i thinks aij is Receiver’s action (default leave & no broadcast)
k
i
if bkj> bij → update and rebroadcast
if bkj= bij & akj< bij → update & rebroadcast
if bkj< bij → update time & rebroadcast
k
if tkj> tij→ update & rebroadcast
if |tkj− tij| < → leave & no broadcast
if tkj< tij→ leave & no rebroadcast
m /∈ {i, k}
if bkj> bij & tkj≥ tij→ update & rebroadcast
if bkj< bij & tkj≥ tij→ leave & rebroadcast
if bkj= bij → leave & rebroadcast
if bkj< bij & tkj< tij→ rebroadcast
if bkj> bij & tkj< tij→ update & rebroadcast
none update & rebroadcast
i
i
if tkj> tij→ update & rebroadcast
if |tkj− tij| < → leave & no-rebroadcast
if tkj< tij→ leave & no rebroadcast
k reset & rebroadcast?
m /∈ {i, k} → leave & rebroadcast none → leave & rebroadcast?
Legend rebroadcast
alone, with leave, broadcast receiver states with update time, broadcast receiver states with update, broadcast sender states with reset, broadcast sender states rebroadcast? broadcast empty bid with current time
Table B.1: Rules table for vinea asynchronous conflict resolution. The sender phys- ical node is denoted with k, and the receiver physical node with i (Table 1 of 2).
k thinks akj is i thinks aij is Receiver’s action (default leave & no broadcast)
m /∈ {i, k}
i
if bkj> bij → update and rebroadcast
if bkj= bij and akj< aij → update and rebroadcast
if bkj< bij → update time and rebroadcast
k
if bkj< bij → update and rebroadcast (sender info)
if tkj> tij → update and rebroadcast
if |tkj− tij| < → leave and no rebroadcast
if tkj< tij → leave and rebroadcast
n /∈ {i, k, m}
if bkj> bij and tkj≥ tij → update and rebroadcast
if bkj< bij and tkj< tij → leave and rebroadcast
if bkj< bij and tkj> tij → update and rebroadcast
if bkj> bij and tkj< tij → leave and rebroadcast
none update and rebroadcast
none
i leave and rebroadcast k update and rebroadcast m /∈ {i, k} update and rebroadcast none leave and no rebroadcast
Legend rebroadcast with leave or update time, broadcast receiver states with update or reset, broadcast sender states
Table B.2: Rules table for vinea asynchronous conflict resolution. The sender phys- ical node is denoted with k, and the receiver physical node with i (Table 2 of 2).
Physical Node Configuration File
C.1
Physical Node Configuration File
vinea.pnetwork.name = PhysicalNetwork1 vinea.pnode.userName = BU
vinea.pnode.passWord = BU
#this is the local TCP port this IPC is going to listen to TCPPort = 21115
vinea.pnode.name = pnode1 #neighbors
#every vinea node should be connected to the ISD neighbour.1 = isd1 neighbour.2 = sliceManagerIPC neighbour.3 = pnode3 ##### DNS configuration ##### dns.name = localhost dns.port = 21111 ##### PN authentication ##### enrollment.authenPolicy =AUTH_PASSWD
##### ISD configuration ##### vinea.isd.name = isd1
### cade Policies ### # unique pnode id cade.id = 3
# SAD, MAD or write your own cade.allocationPolicy = MAD # least or most informative
cade.assignmentVectorPolicy = most # bid vector length
cade.bidVectorLength = 10 # bid (utility) function
cade.nodeUtility = residual_node_capacity # authenticator
cade.owner = sliceManagerIPC # service provider to subscribe cade.mySP = sp
# physical link capacity for to be split among all outgoing hosting flows cade.outgoingLinkCapacity = 100
# physical link capacity for to be split among all incoming hosting flows cade.incomingLinkCapacity = 100
C.2
Service Provider Configuration File
vinea.pnode.name = sp vinea.pnetwork.name = PhysicalNetwork1 vinea.pnode.userName = BU vinea.pnode.passWord = BU TCPPort = 11112#neighbors needs to be set up in advance, like the wires neighbour.1 = idd neighbour.2 = InPManager neighbour.3 = pnode1 neighbour.4 = pnode3 neighbour.5 = pnode2 ### DNS dns.name = localhost dns.port = 21111 vinea.enrollment.authenPolicy =AUTH_PASSWD
##For ISD, only name is needed, the port is queried to the DNS vinea.isd.name = isd
# trusted pnodes
vinea.sp.trusted.1 = pnode1
#vinea.sp.trusted.2 = pnodeName ... # node embedding policies
vinea.sp.vnode.auction = sad # partition size
vinea.sp.partitionSize = 1
# service provider timeout in seconds (if set to -1 waits for response indefinitely) vinea.sp.timeout = -1
[ABC+09] Alvin AuYoung, Phil Buonadonna, Brent N. Chun, Chaki Ng, David C. Parkes, Jeff Shneidman, Alex C. Snoeren, and Amin Vah- dat. Two Auction-Based Resource Allocation Environments: Design and Experience. Market Oriented Grid and Utility Computing, Raj- mukar Buyya and Kris Bubendorfer (eds.), Chapter 23, Wiley, 2009.
[ACSV04] AuYoung, Chun, Snoeren, and Vahdat. Resource Allocation in
Federated Distributed Computing Infrastructures. In Proceeding of Workshop on Operating System and Architecture Support for the On demand Information Technology Infrastructure, October 2004.
[AL12] M. Alicherry and T.V. Lakshman. Network Aware Resource Allo-
cation in Distributed Clouds. In Proceedings of IEEE International Conference on Computer Communications (INFOCOM’12), pages 963 –971, March 2012. doi:10.1109/INFCOM.2012.6195847.
[Amaa] Amazon. Virtual Private Cloud. Available from: http://aws.
amazon.com/vpc/.
[Amab] Amazon.com. Amazon Elastic Computing Cloud (Amazon EC2).
http://aws.amazon.com/ec2/.
[AOVP08] Jeannie Albrecht, David Oppenheimer, Amin Vahdat, and David A. Patterson. Design and Implementation Trade-offs for Wide-Area Re- source Discovery. ACM Transaction of Internet Technologies, 8(4):1– 44, 2008. doi:http://doi.acm.org/10.1145/1391949.1391952. [APST05] Thomas Anderson, Larry Peterson, Scott Shenker, and Jonathan
Turner. Overcoming the Internet Impasse through Virtualization. Computer Communication ACM, 38(4):34–41, 2005.
[BASS11] Theophilus Benson, Aditya Akella, Anees Shaikh, and Sambit Sahu. CloudNaaS: a Cloud Networking Platform for Enterprise Applica- tions. In Proceedings of the 2nd ACM Symposium on Cloud Com- puting, SOCC ’11, pages 8:1–8:13, New York, NY, USA, 2011. ACM. Available from: http://doi.acm.org/10.1145/2038916.2038924, doi:10.1145/2038916.2038924.
[BCMR04] J.W. Byers, J. Considine, M. Mitzenmacher, and S. Rost. In- formed content delivery across adaptive overlay networks. Net- working, IEEE/ACM Transactions on, 12(5):767–780, 2004. doi: 10.1109/TNET.2004.836103.
[Ber01] D. P. Bertsekas. Auction Algorithms. In Encyclopedia of Optimiza- tion, Dec 2001.
[BFH+06] Andy Bavier, Nick Feamster, Mark Huang, Larry Peterson, and Jen-
nifer Rexford. In vini veritas: realistic and controlled network exper- imentation. SIGCOMM ’06: Proceedings of the 2006 conference on Applications, technologies, architectures, and protocols for computer communications, pages 3–14, 2006.
[BLBS06] S. Banerjee, Seungjoon Lee, B. Bhattacharjee, and A. Srinivasan. Resilient Multicast Using Overlays. Networking, IEEE/ACM Trans- actions on, 14(2):237–248, 2006. doi:10.1109/TNET.2006.872579. [BNCV05] Alvin AuYoung Chaki Ng David C. Parkes Jeffrey Shneidman Alex C. Snoeren Brent N. Chun, Philip Buonadonna and Amin Vahdat. Mirage: A microeconomic resource allocation system for sensornet testbeds. In Proceedings of the 2nd IEEE Workshop on Embedded Networked Sensors, 2005.
[BT89] Dimitri P. Bertsekas and John N. Tsitsiklis. Parallel and Distributed Computation: Numerical Methods. Prentice-Hall, Inc., Upper Saddle River, NJ, USA, 1989.
[BXM+10] I. Baldine, Y. Xin, A. Mandal, C. Heermann, J. Chase, V. Maru- padi, A. Yumerefendi, and D. Irwin. Autonomic Cloud Network Or- chestration: A GENI Perspective. In 2nd International Workshop on Management of Emerging Networks and Services (IEEE MENS ’10), in conjunction with GLOBECOM’10, December 2010.
[CAD] Flavio Esposito. Simulator source code. http://csr.bu.edu/cad.
[Cas90] J. Case. A Simple Network Management Protocol (SNMP). ARPA
Request For Comment (RFC) - 1157, May 1990. Available from: ftp://ftp.rfc-editor.org/in-notes/rfc1157.txt.
[CB10] N.M. Mosharaf Kabir Chowdhury and Raouf Boutaba. A Survey
of Network Virtualization. Computer Networks, 54:862–876, April 2010. Available from: http://dx.doi.org/10.1016/j.comnet. 2009.10.017, doi:http://dx.doi.org/10.1016/j.comnet.2009. 10.017.
[CBH09] Han-Lim Choi, Luc Brunet, and Jonathan P. How. Consensus-based Decentralized Auctions for Robust Task Allocation. IEEE Trans- action of Robotics, 25(4):912–926, 2009. doi:http://dx.doi.org/ 10.1109/TRO.2009.2022423.
[CBK10] Kyle Chard, Kris Bubendorfer, and Peter Komisarczuk. High
Occupancy Resource Allocation for Grid and Cloud Systems, a Study with DRIVE. In Proceedings of the 19th ACM Interna- tional Symposium on High Performance Distributed Computing, HPDC ’10, pages 73–84, New York, NY, USA, 2010. ACM. Avail- able from: http://doi.acm.org/10.1145/1851476.1851486, doi: http://doi.acm.org/10.1145/1851476.1851486.
[CBMP04] Jeffrey Considine, John W. Byers, and Ketan Meyer-Patel. A con- straint satisfaction approach to testbed embedding services. SIG- COMM Computer Communication Review, 34(1):137–142, 2004. doi:http://doi.acm.org/10.1145/972374.972398.
[CJ09] Jorge Carapinha and Javier Jimenez. Network virtualization—a view from the bottom. VISA, ACM SIGCOMM Workshop on Virtualized Infastructure Systems and Architectures, 17 August 2009.
[CNA+04] Brent N. Chun, Chaki Ng, Jeannie Albrecht, David C. Parkes, and
Amin Vahdat. Computational resource exchanges for distributed resource allocation. 2004.
[CR09] H.L. Chen and T. Roughgarden. Network Design with Weighted
Players. Theory of Computing Systems, 45(2):302–324, 2009.
[CRB09] Mosharaf Kabir Chowdhury, Muntasir Raihan Rahman, and Raouf
Boutaba. Virtual Network Embedding with Coordinated Node and Link Mapping. In INFOCOM, pages 783–791, 2009.
[CSB10] Mosharaf Chowdhury, Fady Samuel, and Raouf Boutaba. PolyViNE: Policy-Based Virtual Network Embedding Across Multiple Domains. In Proc. of ACM SIGCOMM workshop on Virtualized Infrastruc- ture Systems and Arch., VISA ’10, pages 49–56, New York, NY, USA, 2010. ACM. Available from: http://doi.acm.org/10.1145/ 1851399.1851408, doi:http://doi.acm.org/10.1145/1851399. 1851408.
[CSZ+11] Xiang Cheng, Sen Su, Zhongbao Zhang, Hanchi Wang, Fangchun
Yang, Yan Luo, and Jie Wang. Virtual Network Embedding Through Topology-Aware Node Ranking. SIGCOMM Computer Communi- cation Review, 41:38–47, April 2011. Available from: http://doi.
acm.org/10.1145/1971162.1971168, doi:http://doi.acm.org/ 10.1145/1971162.1971168.
[CV03] B. Chun and A. Vahdat. Workload and Failure Characterization on a Large-Scale Federated Testbed. Technical report, IRB-TR-03-040, Intel Research Berkeley, 2003.
[CW09] Costas Courcoubetis and Richard R. Weber. Economic Issues in
Shared Infrastructures. VISA ’09: Proceedings of the 1st ACM workshop on Virtualized infrastructure systems and architectures, pages 89–96, 2009. doi:http://doi.acm.org/10.1145/1592648. 1592663.
[CYB+ed] Jeff Chase, Aydan Yumerefendi, Ilia Baldine, Yuefeng Xin, Anir-
ban Mandal, and Chris Heerman. Cloud Network Infrastructure as a Service: An Exercise in Multi-Domain Orchestration. Dec 2010 (unpublished).
[Dan13] Daniel Jackson. Alloy. http://alloy.mit.edu/alloy/, 2013.
[Dat13] Database For Objects. http://www.db40.com, 2013.
[Dav02] David G. Andersen. Theoretical Approaches to Node Assignment. Unpublished Manuscript, http://www.cs.cmu.edu/~dga/papers/ andersen-assign.ps, 2002.
[Day08] J. Day. Patterns in Network Architecture: A Return to Fundamen- tals. Prentice Hall, 2008.
[DGG+99] Nick G. Duffield, Pawan Goyal, Albert G. Greenberg, Partho Pra-
tim Mishra, K. K. Ramakrishnan, and Jacobus E. van der
Merwe. A Flexible Model for Resource Management in
Virtual Private Networks. In Proceedings Conference on
Applications, Technologies, Architectures, and Protocols for Computer Communications (SIGCOMM), pages 95–108, 1999. Available from: http://dblp.uni-trier.de/db/conf/sigcomm/ sigcomm1999.html#DuffieldGGMRM99.
[DGG+02] N. G. Duffield, Pawan Goyal, Albert Greenberg, Partho Mishra, K. K. Ramakrishnan, and Jacobus E. van der Merwe. Resource management with hoses: point-to-cloud services for virtual private networks. IEEE/ACM Transaction of Networking, 10(5):679–692, 2002.
[DK09] Nikhil R. Devanur and Sham M. Kakade. The Price of Truthful-
conference on Electronic commerce, EC, pages 99–106, New York, NY, USA, 2009. Available from: http://doi.acm.org/10.1145/ 1566374.1566388, doi:10.1145/1566374.1566388.
[DL07] Qiang Duan and Enyue Lu. Network Service Description and Dis-
covery for the Next Generation Internet. In Proceedings of the 19th IASTED International Conference on Parallel and Distributed Computing and Systems, PDCS ’07, pages 509–514, Anaheim, CA, USA, 2007. ACTA Press. Available from: http://dl.acm.org/ citation.cfm?id=1647539.1647632.
[DMM08] John Day, Ibrahim Matta, and Karim Mattar. Networking is
IPC: A Guiding Principle to a Better Internet. In Proceed- ings of the 2008 ACM International Conference on Emerging Networking Experiments and Technologies (CoNEXT), CoNEXT ’08, pages 67:1–67:6, New York, NY, USA, 2008. ACM. Avail- able from: http://doi.acm.org/10.1145/1544012.1544079, doi: http://doi.acm.org/10.1145/1544012.1544079.
[dVV03] Sven de Vries and Rakesh V. Vohra. Combinatorial auctions: A sur- vey. INFORMS Journal on Computing, (3):284–309, 2003. Available from: citeseer.ist.psu.edu/devries01combinatorial.html. [EDM13] Flavio Esposito, Donato Di Paola, and Ibrahim Matta. A General
Distributed Approach to Slice Embedding with Guarantees. In Pro- ceedings of the IFIP International Conference on Networking, Net- working 2013, Brooklyn, NY, USA, 2013.
[EM09] Flavio Esposito and Ibrahim Matta. PreDA: Predicate routing for DTN architectures over MANET. In In Proceedings of IEEE Global Telecommunications Conference (GLOBECOM), pages 1–6. IEEE, November 2009. Available from: http://dx.doi.org/10.1109/ GLOCOM.2009.5425372, doi:10.1109/GLOCOM.2009.5425372. [EMI13] Flavio Esposito, Ibrahim Matta, and Vatche Ishakian. Slice Embed-
ding Solutions for Distributed Service Architectures. ACM Compu- ing Surveys (Accepted Nov 2012, to appear), 46(2), June 2013.
[Epp99] David Eppstein. Finding the k Shortest Paths. SIAM Journal
of Computing, 28(2):652–673, 1999. doi:http://dx.doi.org/10. 1137/S0097539795290477.
[Esp13] Esposito Flavio. The Virtual Network Embedding Architecture
[EWMD] Flavio Esposito, Yuefeng Wang, Ibrahim Matta, and John Day. Recursive InterNetwork Architecture (RINA): A Prototype. In 11th Boston University Industrial Affiliates Program (IAP) Research Day. Abstract and Poster. April. doi:http://www.cs.bu.edu/IAP/ ResearchDay2011/IAP11.pdf.
[EWMD12] Flavio Esposito, Yuefeng Wang, Ibrahim Matta, and John
Day. RINA: An Architecture for Policy-Based Dynamic Ser- vice Composition. In 12th Boston University Industrial Affil- iates Program (IAP) Research Day. Abstract and Poster. 23rd March, 2012. doi:http://www.cs.bu.edu/IAP/ResearchDay2012/ ABSTRACT/iap2012abs_atxt.html.
[EWMD13] Flavio Esposito, Yuefeng Wang, Ibrahim Matta, and John Day. Dy- namic Layer Instantiation as a Service. In Demo at USENIX Sym- posium on Networked Systems Design and Implementation (NSDI 2013), Lombard, IL, April 2013.
[FA06] Jinliang Fan and Mostafa H. Ammar. Dynamic topology configura- tion in service overlay networks: A study of reconfiguration policies. In In Proceeding of Conference of the IEEE Computer and Commu- nications Societies (INFOCOM), 2006.
[FBCB10] Nabeel Farooq Butt, Mosharaf Chowdhury, and Raouf Boutaba.
Topology-Awareness and Reoptimization Mechanism for Virtual Network Embedding. In Proceedings of the 9th IFIP TC 6 inter- national conference on Networking, pages 27–39, Berlin, Heidelberg, 2010. Springer-Verlag. Available from: http://dx.doi.org/10. 1007/978-3-642-12963-6_3, doi:10.1007/978-3-642-12963-6_ 3.
[FCC+03] Yun Fu, Jeffrey Chase, Brent Chun, Stephen Schwab, and Amin
Vahdat. Sharp: an architecture for secure resource peering. SIGOPS Operating System Review, 37(5):133–148, 2003. doi:http://doi. acm.org/10.1145/1165389.945459.
[Fei98] Uriel Feige. A Threshold of ln n for Approximating Set Cover. J. ACM, 45(4):634–652, July 1998.
[FFK+06] Ian T Foster, Timothy Freeman, Katarzyna Keahey, Doug Scheft-
ner, Borja Sotomayor, and Xuehai Zhang. Virtual Clusters for Grid Communities. In Proceedings of the Sixth IEEE International Sym- posium on Cluster Computing and the Grid (CCGRID ’06), pages 513–520. IEEE Computer Society, 2006.
[FGR07] Nick Feamster, Lixin Gao, and Jennifer Rexford. How to lease the internet in your spare time. SIGCOMM Computer Commu- nication Review, 37(1):61–64, 2007. doi:http://doi.acm.org/10. 1145/1198255.1198265.
[GEN07] GENI End-user Opt-in Working Group. Genioptin, March 2007.
Available from: http://groups.geni.net/geni/wiki/GeniOptIn. [GEN11] GENI. Stitching Architecture Proposal. http://geni.maxgigapop.
net/twiki/bin/view/GENI/NetworkStitching, 2011.
[GHJ+09] Albert G. Greenberg, James R. Hamilton, Navendu Jain, Srikanth
Kandula, Changhoon Kim, Parantap Lahiri, David A. Maltz, Parveen Patel, and Sudipta Sengupta. Vl2: a scalable and flexible data center network. In Pablo Rodriguez, Ernst W. Biersack, Kon- stantina Papagiannaki, and Luigi Rizzo, editors, SIGCOMM, pages 51–62. ACM, 2009. Available from: http://dblp.uni-trier.de/ db/conf/sigcomm/sigcomm2009.html#GreenbergHJKKLMPS09. [Glo09] Global Environment for Network Innovations. http://www.geni.net,
2009.
[Goo13] Google Buffer Protocol. Developer Guide http://code.google.
com/apis/protocolbuffers, 2013.
[gri03] The Grid. Blueprint for a New Computing Infrastructure.: Blueprint for a New Computing Infrastructure (Elsevier Series in Grid Com- puting). Morgan Kaufmann, 2. a. edition, December 2003. Avail- able from: http://www.amazon.com/exec/obidos/redirect?tag= citeulike07-20&path=ASIN/1558609334.
[HAD+12] Dongsu Han, Ashok Anand, Fahad Dogar, Boyan Li, Hyeontaek Lim, Michel Machado, Arvind Mukundan, Wenfei Wu, Aditya Akella, David G. Andersen, John W. Byers, Srinivasan Seshan, and Pe- ter Steenkiste. XIA: Efficient support for evolvable internetworking. In Proc. 9th USENIX Network Systems Design and Implementation (NSDI), San Jose, CA, April 2012.
[Hay08] Brian Hayes. Cloud computing. Commun. ACM, 51(7):9–11, 2008.
doi:http://doi.acm.org/10.1145/1364782.1364786.
[HB09] Urs Hoelzle and Luiz Andre Barroso. The Datacenter as a Com-
puter: An Introduction to the Design of Warehouse-Scale Machines. Morgan and Claypool Publishers, 2009.
[HLBAZ11] Ines Houidi, Wajdi Louati, Walid Ben Ameur, and Djamal Zegh- lache. Virtual Network Provisioning across Multiple Substrate Net- works. Computer Networks, 55(4):1011–1023, March 2011. Avail- able from: http://dx.doi.org/10.1016/j.comnet.2010.12.011, doi:10.1016/j.comnet.2010.12.011.
[HLZ08] I. Houidi, W. Louati, and D. Zeghlache. A Distributed Virtual Network Mapping Algorithm. In IEEE International Conference on Communications (ICC), pages 5634 –5640, May 2008. doi: