electrical and computer engineering, university of thessaly

66
Vasilis Sourlas – PhD defense – 23/7/2013 Electrical and Computer Engineering, University of Thessaly “Replication Management and Cache aware Routing in Information-Centric Networking” Vasilis Sourlas Dissertation Committee: Leandros Tassiulas (UTH,GR), Supervisor Spyros Lalis (UTH, GR) George Pavlou (UCL, UK) 1

Upload: lucien

Post on 23-Feb-2016

44 views

Category:

Documents


0 download

DESCRIPTION

Electrical and Computer Engineering, University of Thessaly. “Replication Management and Cache aware Routing in Information-Centric Networking” Vasilis Sourlas. Dissertation Committee: Leandros Tassiulas (UTH,GR), Supervisor Spyros Lalis (UTH, GR) George Pavlou ( UCL, UK ). Outline. - PowerPoint PPT Presentation

TRANSCRIPT

Slide 1

Electrical and Computer Engineering, University of Thessaly

Replication Management and Cache aware Routing in Information-Centric Networking

Vasilis SourlasDissertation Committee: Leandros Tassiulas (UTH,GR), SupervisorSpyros Lalis (UTH, GR)George Pavlou (UCL, UK)1

Vasilis Sourlas PhD defense 23/7/20131Outline1) Introduction2) Replication Management Framework3) Storage Planning and Off-line Replica Assignment4) Distributed Cache Management5) Opportunistic Caching6) Cache Aware Routing7) Conclusions and Future Work2Vasilis Sourlas PhD defense 23/7/2013Outline1) Introduction2) Replication Management Framework3) Storage Planning and Off-line Replica Assignment4) Distributed Cache Management5) Opportunistic Caching6) Cache Aware Routing7) Conclusions and Future Work3Vasilis Sourlas PhD defense 23/7/2013Internet-based ContentThe vast majority of interactions relate to content access:P2P overlays (BitTorrent)Media aggregators (YouTube)Content Delivery Networks (Akamai)Social Networks (Facebook)Photo sharing sites (Picasa)New approaches are required to cater for the explosion of video-based content and for creating novel use experiences.Continue throwing more capacity cannot work anymore!4

Vasilis Sourlas PhD defense 23/7/2013Expected IP Traffic Growth 2012-2017According to the Cisco Visual Networking Index:Global IP traffic will reach 1.3 zettabytes per year.3 networked devices per capita in 2016 vs 1 per capita in 2011.15 GBytes per capita IP traffic in 2016 vs 4 GBytes in 2011.Approx. 55% of the overall Internet traffic will be video by 2016, without counting P2P video file sharing (~ 86% including P2P).It will take over 5 years to watch the amount of video that will cross global IP networks every second in 2015!!

What is exchanged is becoming more important than who are exchanging it.5Vasilis Sourlas PhD defense 23/7/2013Information-Centric NetworkingParadigm shift from the host-to-host Internet to a host-to-content one.Information-Centric Networking (ICN) targets a general infrastructure that provides in-network caching and multicast communication so that content is distributed in a scalable, cost-efficient & secure manner.6Vasilis Sourlas PhD defense 23/7/2013ICN Architectural ModelsInformation-centric (Content-Centric) networksContent is explicitly named.Subscriptions/Interests act on the name of each packet. One-time fetch and ongoing subscribe operation. DONA, PURSUIT, NDN/CCN, SAIL, ... Content-Based Publish/Subscribe (CBPS) networksOverlay event notification services.Broader request semantics (attribute/value scheme).One-time fetch only operation.No content servers assumed. IBM Gryphon, Siena, REDS, Elvin,

7Vasilis Sourlas PhD defense 23/7/2013CCN Operation

InterestDataCheck Pending Interests Table8

Check Content StoreCheck Pending Interests TableCheck Forwarding Information BaseS1: /spiegel.com/crisisingreece/news.pdf/page34/....S1: /spiegel.com/crisisingreece/news.pdf/page34/....Check Content StoreVasilis Sourlas PhD defense 23/7/20138

CBPS OperationS1: [type,=,movie/english], [artist,=,Bruce Lee],[year,=,*]

Subscribe ( )

Subscribe( )

Publish( )S2: [type,=,music/mp3], [artist, =, madonna], [album, =, *], [year, >, 1990]9P: [type,=,movie/english], [artist, =, Bruce Lee, Chuck Norris], [title, =, BLvsCN.avi]Vasilis Sourlas PhD defense 23/7/20139Research ChallengesInformation-Centric Networking Research Group (ICNRG)Cache management Traffic engineeringScalable Routing QoS approachesNovel caching strategies.10Vasilis Sourlas PhD defense 23/7/2013Work SynopsisCDN-like replication management framework. In-network opportunistic caching framework.Cache aware routing scheme.11Vasilis Sourlas PhD defense 23/7/2013Outline1) Introduction2) Replication Management Framework3) Storage Planning and Off-line Replica Assignment4) Distributed Cache Management5) Opportunistic Caching6) Cache Aware Routing7) Conclusions and Future Work12Vasilis Sourlas PhD defense 23/7/2013IntroductionCDN-like replication distributes a sites content across multiple mirror servers.A request is redirected to the closest server.Replication is used to increase availability and fault tolerance.Side effects: load balancing and enhanced publisher/subscriber proximity.13Vasilis Sourlas PhD defense 23/7/2013ContributionsA three phase replication management framework for ICN Planning phaseDecides the placement of the replication points.Off-line Assignment phaseAssignment of information items to the replication points based on the observed popularity. Generalized assignment problem (reduced to NP-complete multiple knapsack problem).On-line Replacement phaseReplacement of information items in real-time, based on the changing demand pattern.14Vasilis Sourlas PhD defense 23/7/2013Replication Framework (off-line)StoragePlanningReplicaAssignmentSubscriptionForecastNetworkTopologySubDataLong-term forecastMedium-long term forecastConfigure (subscribe item t1, publish item t1)Configure (subscribe item t2, publish item t2)Monitor subscriptions

Storage deviceStorage deviceSubscribersSubscribersForwardingNodesForwardingNodes15Monitoring each nodeVasilis Sourlas PhD defense 23/7/2013Replication Framework (dynamic)16

Replace item i with item j?client request rates, topology, cache configscoordinate decisionsClients request for itemsCache enabled ICN nodeCache Replacement SubstrateCache ManagersVasilis Sourlas PhD defense 23/7/2013Outline1) Introduction2) Replication Management Framework3) Storage Planning and Off-line Replica Assignment4) Distributed Cache Management5) Opportunistic Caching6) Cache Aware Routing7) Conclusions and Future Work17Vasilis Sourlas PhD defense 23/7/2013IntroductionReplication is thoroughly investigated in the area of CDNs (approximate solutions and optimal algorithms for tree topologies).2-aproximation algorithms have been proposed also in the area of distributed replication groups.In ICN only approaches based on distributed databases.Less attention has been given to network constraints (limited storage capacity).

18Vasilis Sourlas PhD defense 23/7/2013ContributionsEnhanced the CBPS with an advertisement and a request/response mechanism.Modified known Greedy algorithm (CDN context).Used the modified greedy for the proposed placement algorithm.Proposed a new algorithm for the selection of R storage points among the V network nodes (R < V) based on: a) the locality and the popularity of the interests for each item b) the targeted replication degree km of each item m c) the storage capacity L of each replication deviceProposed two alternative assignment mechanisms.Target - Minimize clients response latency subject to installing the minimum number (or any given number) of replicas in the network.

19Vasilis Sourlas PhD defense 23/7/2013Greedy Algorithm1st round: evaluates each of the V nodes to determine its suitability to become a storage. Computes the Gain (traffic served by replica and does not need to access original server) associated with each node and selects the one that maximizes the Gain.2nd round: searches for a second storage which, in conjunction with the storage already picked, yields the highest Gain.Completes: iterates until the requested number of storages have been chosen for the replication of the specific server.

20Vasilis Sourlas PhD defense 23/7/2013No knowledge of the location of the server, differently there is no server at all.Repeat Greedy alg V times (server j is a different node of the network). V vectors of possible storages.Choose as our storages those nodes that appeared more times in the per element summation of the V vectors.Modified Greedy Algorithm21Vasilis Sourlas PhD defense 23/7/2013Planning and AssignmentSteps:For each item m we execute the modified greedy algorithm and we get M vectors of possible storages.Each vector is weighted by each items weight (significance regarding the traffic of each item in the network).Select as storages those M nodes that appeared more times in the per element weighted summation of the M vectors.For each item m starting from the most significant (based on the weight) assign km storages following the procedure below:For each entry in the vector of item m calculated in step 1 assign a storage if that entry also appears in the final storage nodes calculated in step 3 and only if in that storage has been assigned less than L items until we get km storages.A similar weighted round robin-like mechanism based on the weight of each item has also been proposed.22PlanningAssignmentVasilis Sourlas PhD defense 23/7/2013Compare to:grd_opt: each item m is assigned to the km storages produced by the first step of the placement algorithmrnd: no differentiation among items, random assignment after the selection of the storagesMetrics:Mean hop distance between the requesting client and the storage (indicative of the response latency)Evaluation23Vasilis Sourlas PhD defense 23/7/201324

Predefined Minimum Replication DegreeOff-line Assignment Phase Evaluation

Vasilis Sourlas PhD defense 23/7/2013The proposed planning and the two off-line placement algorithms perform only 1%-5% worse than greedy, using 50%-80% less storages.Appropriate solution for real world scenarios where a storage provider has limitations in the number of replicas that can install.Results25Vasilis Sourlas PhD defense 23/7/2013Outline1) Introduction2) Replication Management Framework3) Storage Planning and Off-line Replica Assignment4) Distributed Cache Management5) Opportunistic Caching6) Cache Aware Routing7) Conclusions and Future Work26Vasilis Sourlas PhD defense 23/7/2013ContributionsProposed a distributed cache management architecture that dynamically (re-)assigns information items to caches, based on items demand patterns in order to minimize the overall network traffic.Presented four distributed on-line cache management algorithms, categorized them based on the level of cooperation needed between the managers and compared them against their performance, complexity, message overhead and convergence time.Derived a lower bound of the overall network traffic for regular network topologies.27Vasilis Sourlas PhD defense 23/7/2013Distributed Cache Management ArchitectureDistributed Cache Managers (CM) decide in a coordinated manner whether to cache an item and replace an already cached.Every CM should have a holistic network-wide view of all the cache configurations and the demand patterns.Upon a change in a cache configuration the CM should inform (event-based manner) every other CM in the network. 28Vasilis Sourlas PhD defense 23/7/2013Distributed On-Line Cache Manage-ment Algorithms Known global demand patterns and global replica placement (global cache configu-ration), minimize overall network trafficCooperative Cache Management Algorithm Holistic Cache Management AlgorithmHolistic-all Cache Management Algorithm

Known local demand patterns and global replica placement, minimize local traffic (local clients)4. Myopic Cache Management Algorithm

29Vasilis Sourlas PhD defense 23/7/2013Cooperative Algorithm Each CM computes:For each item m in the cache the performance loss lm if item m is removed from the cache.For each item m not in the cache of the performance gain gm if item m is cached.Candidate for insertion the item of maximum performance gain.Candidate for replacement the items of minimum performance loss.Maximum local relative gain r= gm - lm and report it to the rest CMs.CMs calculate the most network-wide beneficial replacement and updated their configuration matrix. Steps 1-2 are repeated until no further replacements are beneficial for the network.

Each replacement decreases the overall network traffic -converges to an equilibrium point (local minimum given the initial cache configuration).

Vasilis Sourlas PhD defense 23/7/201330Holistic Algorithm Holistic-all AlgorithmOnly one CM runs the algorithm at a time e.g. token based decision making.In holistic only one replacement at each node per iteration.In holistic-all all possible replacements at each node per iteration.

31Vasilis Sourlas PhD defense 23/7/2013Myopic AlgorithmIn highly dynamic environments each CM may dont have info about the demand pattern in the network.Decision based on local info only w.r.t to local requests but every CM is aware of the global cache configurations.Each CM calculates its replacements in order to minimize the traffic cost for the demand it serves.Same decision making as the holistic.32Vasilis Sourlas PhD defense 23/7/2013Network Traffic Lower BoundAssumptionsUniform request pattern.Unit size information items.Regular network topologies (distance regular graphs, n-dim torus).Theorem:

33

Vasilis Sourlas PhD defense 23/7/2013EvaluationMetrics:Overall network traffic, ONT (reqs*hops/sec) at equilibrium.Total number of replacements per node, RE.Total number of iterations per node, IT (indicative of the running time).

Two sets of experimentsUniform demand patternSynthetic workload & Zoo Topologies34Vasilis Sourlas PhD defense 23/7/2013Uniform Demand Pattern35

Vasilis Sourlas PhD defense 23/7/2013Synthetic Workload & Zoo Topologies36

Vasilis Sourlas PhD defense 23/7/201336Convergence & Mean Cache Hit Distance37

Vasilis Sourlas PhD defense 23/7/2013ResultsThe algorithms that use network-wide information are near optimal since the corresponding difference from the lower bound varies between 0,5% and 3,6% regardless of the topology, the size of the network and the storing capacity of each cache and the initial cache assignment.Network wide knowledge and cooperation give significant performance benefits and reduce the time to convergence at the cost of additional message exchanges and computational effort.

38Vasilis Sourlas PhD defense 23/7/2013Outline1) Introduction2) Replication Management Framework3) Storage Planning and Off-line Replica Assignment4) Distributed Cache Management5) Opportunistic Caching6) Cache Aware Routing7) Conclusions and Future Work39Vasilis Sourlas PhD defense 23/7/2013IntroductionIn-network opportunistic caching is a salient characteristic of ICNs.Caching in ICN takes as granted the presence of a hosting server (caches are used to improve delivery of popular items).In CBPS implementations (or in future P2P ICN implementations) servers do not exist.

Caching to preserve information over time instead of making information available in nearer space is missing.40Vasilis Sourlas PhD defense 23/7/2013ContributionsEnhanced CBPS with a req/resp scheme (subscribers can retrieve already published items).Decomposed caching mechanism is a set of basic poli-cies/strategies (proposed ICN oriented at each set).Proposed two duplicate dropping mechanisms (proactive & reactive).Proposed a stochastic model that captures the dynamics of the new ICN oriented policies.Described a prototype implementation of the proposed caching mechanisms (Planetlab).Modified the proposed caching scheme to support mobility of subscribers. 41Vasilis Sourlas PhD defense 23/7/2013PoliciesCaching selects a number of nodes and assigns them as caching points.Selective caching (SEL)En-route caching (NRT)Placement/Replacement - decides a position in the cache where a new message will be cached and which message will be discarded in case of an overflow.Least Recently Used policy (LRU)Least Frequently Used policy (LFU)Priority policy (PRT)Request dictates how requests (interests) are propagated in the network. Subscription-based request policy (SUB)Flooding request policy (FLD)42Vasilis Sourlas PhD defense 23/7/2013Reactive mechanism, nodes check passing responses whether the item is in its Cache. If true, discards the response packet (Responses follow backwards the same path with Requests).Proactive mechanism, responded node/cache appends to the Requests APID (Aggregated Publication Ids) the pub-id of the responded item. Recipients of the request respond with cached items which pub-id are not in the Request.Handling Multiple Responses43Vasilis Sourlas PhD defense 23/7/2013Stochastic Cache ModelingUse Absorbing Markov Processes to compute the Mean Absorption Time (AT). of an item in the caches of the network.Present analytical results for a single node network (~ multi-node scenario without item copying).Reduce the state space with an approxi-mation.Use the reduced space for the multi-node scenario.44Vasilis Sourlas PhD defense 23/7/2013Mobility SupportA mechanism that uses a portion of a proxys buffer. Manages subscriptions and publications on behalf of the Mobile Node (MN).When the MN is disconnected, stores items matching MNs interests.During the switch-over phase (reconnection phase) delivers stored items to the MN.45Vasilis Sourlas PhD defense 23/7/2013EvaluationImplemented the framework in a Java-based overlay framework/REDS and in a discrete event simulator using MATLAB.Compared the analytical model with discrete event simulations.Planetlab and simulation experimentation of various combinations of opportunistic caching schemes.

Metrics:Mean Absorption time, AT caching capability of the networkMinimum hop distance delay, perceived QoSTraffic Overhead replication and overheadSatisfaction perceived QoS

46Vasilis Sourlas PhD defense 23/7/2013Planetlab experimentation47

Vasilis Sourlas PhD defense 23/7/2013ResultsThe newly proposed ICN oriented policies outperform traditional ones.The two duplicate dropping mechanisms minimizes the traffic overhead significantly even when used with the flooding request policy.The Markov model is accurate enough, but looses accuracy when the number of nodes increases. Prototype implementation results are inline with discrete-event simulator outcome.48Vasilis Sourlas PhD defense 23/7/2013Outline1) Introduction2) Replication Management Framework3) Storage Planning and Off-line Replica Assignment4) Distributed Cache Management5) Opportunistic Caching6) Cache Aware Routing7) Conclusions and Future Work49Vasilis Sourlas PhD defense 23/7/2013IntroductionPerformance management and traffic engineering approaches are required in ICN to control routing, configure cache replacement policies, etc.Routing functionalities is completely missing from the current ICN design.Only flooding or OSPF-like shortest path mechanisms have been proposed.Recently hash-routing (similar to datacenters) has been proposed to maximize cache hit within a domain regardless of the traffic. 50Vasilis Sourlas PhD defense 23/7/2013ContributionsProposed a novel cache aware intra-domain routing scheme that dynamically computes the paths followed by each subscription/interest for each item and from each node in the network.Presented a Dynamic Programming (DP) approach for the computation of the cheapest transportation paths based on the observed item request patterns, in order to minimize the overall transportation cost imposed by the user requests.Proposed an iterative algorithm for those scenarios where the routing decisions interact with the caching strategy. Presented a resource management system architecture for the cache aware routing in ICN. 51Vasilis Sourlas PhD defense 23/7/2013Problem Formulation52

Vasilis Sourlas PhD defense 23/7/2013

53Problem FormulationVasilis Sourlas PhD defense 23/7/2013

54Problem FormulationVasilis Sourlas PhD defense 23/7/2013Motivation Example1PA + 2(1-PA)PC+ 3(1-PA)(1-PC)PE+ 4 (1-PA)(1-PC)(1-PE)1 = 2.1 hopsIn-network cache hit probability = PA + (1-PA)PC+ (1-PA)(1-PC)PE = 0.81PA + 2(1-PA)PB+ 3(1-PA)(1-PB)PD+ 4 (1-PA)(1-PB)(1-PD) PE + 5 (1-PA)(1-PB)(1-PD) (1-PE ) 1 = 1.63 hopsIn-network cache hit probability = PA + (1-PA)PB+ (1-PA)(1-PB)PD+ (1-PA)(1-PB)(1-PD) PE = 0.99

Shortest pathOur shortest pathCaching probabilities of itemP = 0.5P = 0.8P = 0.5P = 0.2P = 0.8ABDCESubscriber requests Sid/RidPublisher of Sid/Rid55Vasilis Sourlas PhD defense 23/7/2013Dynamic Programming approach

56Vasilis Sourlas PhD defense 23/7/2013Iterative AlgorithmCache hit ratio of each item is not indepe-ndent from node to node.Iteratively execute the DP algorithm and observe the network performance until the cache hit ratios of each item converge.At convergence the DP algorithm computes the same paths as long as the demand pattern remains stable.

57Vasilis Sourlas PhD defense 23/7/2013EvaluationCompare the cache aware routing scheme (CAWR) to the shortest path routing scheme (SHPT).Metrics:Total Transportation Cost, TTC (resps*hops/sec)Server Hit Ratio, SHR (reqs/sec)

58Vasilis Sourlas PhD defense 23/7/2013Synthetic Workload & Zoo Topologies59

Vasilis Sourlas PhD defense 23/7/2013ResultsCAWR outperforms SHPT 15%-20% improvement regarding TTC and 35%-45% regarding SHR.The SHR improvement is almost twice as much as the improvement in the TTC. Even if we cannot alleviate the TTC, we can at least achieve significantly better utilization of the network resources and reduce the load at the hosting servers and the need of replication devices.CAWR is robust enough and requires a recalculations of the paths only after extreme changes in the demand pattern.60Vasilis Sourlas PhD defense 23/7/2013Outline1) Introduction2) Replication Management Framework3) Storage Planning and Off-line Replica Assignment4) Distributed Cache Management5) Opportunistic Caching6) Cache Aware Routing7) Conclusions and Future Work61Vasilis Sourlas PhD defense 23/7/2013Replication ManagementPresented a three phase replication framework:Planning phaseA modified ICN oriented greedy algorithm.Offline assignment phaseTwo replica assignment algorithms.On-line replacement phaseFour distributed on-line cache management algs.A lower bound (overall network traffic) for regular network topologies.

In-network opportunistic cachingProposed a new opportunistic caching mechanism.Decompose it in a set of basic policies.Proposed a Markov stochastic model.Described a prototype implementation and evaluate it in Planetlab.Modification of the mechanism to enable mobility of the subscribers.

62Vasilis Sourlas PhD defense 23/7/2013Cache aware routingPresented a new cache aware intra-domain routing scheme.Proposed DP approach for the computation of the minimum transportation cost paths.Proposed an iterative algorithm when routing interacts with caching schemes.

Future Work- Core workDifferent objectives and SLAs among the storage provider and the content providers.Combine opportunistic caching with replication nodes.Enhance routing scheme with multiple servers and traffic engineering schemes.- ICN areaSecurity/anomaly detection.Seamless mobility.Energy Efficient usage of ICN resources.Pricing schemes for the new ICN paradigm.

63Vasilis Sourlas PhD defense 23/7/2013Related PublicationsBook chapter[B.01] Vasilis Sourlas, Paris Flegkas, Dimitrios Katsaros and Leandros Tassiulas, Content Replication and Delivery in Information-Centric Networks, to appear in Advanced Content Delivery and Streaming in the Cloud by Wiley Publishers, USA.Journal publications[J.04] Vasilis Sourlas, Paris Flegkas and Leandros Tassiulas, A Novel Cache Aware Routing Scheme for Information-Centric Networks, submitted in Computer Networks Elsevier.[J.03] Vasilis Sourlas, Lazaros Gkatzikis, Paris Flegkas and Leandros Tassiulas, Distributed Cache Management in Information-Centric Networks, to appear in IEEE Transaction on Network and Service Management (TNSM), 2013.[J.02] Mohamed Diallo, Vasilis Sourlas, Paris Flegkas, Serge Fdida, and Leandros Tassiulas, A Content-Based Publish/Subscribe framework for Large-scale Content Delivery, in Computer Networks Elsevier, Volume 57, Issue 4, pp. 924-943, March 2013.[J.01] Vasilis Sourlas, Paris Flegkas, Georgios S. Paschos, Dimitrios Katsaros, and Leandros Tassiulas, Storage Planning and Replica Assignment in Content-Centric Publish/Subscribe Networks, in S.I. on Internet-based Content Delivery, Computer Networks Elsevier, Volume 55, Issue 18, pp. 4021-4032, December 2011.Conference publications[C.13] Vasilis Sourlas, Paris Flegkas and Leandros Tassiulas, Cache-Aware Routing in Information- Centric Networks, in IFIP/IEEE International Symposium on Integrated Network Management (IM 2013), pp. 582-588, Ghent, Belgium, 2013.[C.12] Vasilis Sourlas and Leandros Tassiulas, Effective Cache Management and Performance Limits in ICN, in International Conference on Computing, Networking and Communications (ICNC 2013), pp. 955-960, San Diego, USA, 2013.[C.11] Paris Flegkas, Vasilis Sourlas, George Parisis and Dirk Trossen, Storage Replication in Information-Centric Networking, in International Conference on Computing, Networking and Communications (ICNC 2013), pp. 850-855, San Diego, USA, 2013.[C.10] Vasilis Sourlas, Paris Flegkas, Lazaros Gkatzikis and Leandros Tassiulas, Autonomic Cache Management in Information-Centric Networks, in 13th IEEE/IFIP Network Operations and Management Symposium (NOMS 2012), pp. 121-129, Hawaii, USA, April 2012.

64Vasilis Sourlas PhD defense 23/7/201364Conference publications (contd)[C.09] Dirk Trossen, Xenofon Vasilakos, Paris Flegkas, Vasilis Sourlas and George Parisis, Mobility Work Re-Visited Not Considered Harmful, in IEEE WMCNT 2011, pp. 1-8, Budapest, Hungary, October 2011.[C.08] Vasilis Sourlas, Lazaros Gkatzikis and Leandros Tassiulas, On-Line Storage Management with Distributed Decision Making for Content-Centric Networks, in 7th Conference on Next Generation Internet (NGI) 2011, pp. 1-8, Kaiseslautern, Germany, June 2011.[C.07] Mohamed Diallo, Serge Fdida, Vasilis Sourlas, Paris Flegkas and Leandros Tassiulas, Leveraging caching for Internet-scale content-based publish/subscribe networks, in IEEE ICC 2011, pp. 1-5, Kyoto, Japan, June 2011.[C.06] Vasilis Sourlas, Georgios S. Paschos, Petteri Mannersalo, Paris Flegkas and Leandros Tassiulas, Modeling the dynamics of caching in content-based publish/subscribe systems, in 26th ACM Symposium On Applied Computing (SAC), Taiwan, March 2011.[C.05] Vasilis Sourlas, Paris Flegkas, Georgios S. Paschos, Dimitrios Katsaros and Leandros Tassiulas, Storing and Replication in Topic-Based Publish/Subscribe Networks, in IEEE Globecom 2010 Next-Generation Networking and Internet Symposium,Miami, USA, December 2010.[C.04] Vasilis Sourlas, Georgios S. Paschos, Paris Flegkas and Leandros Tassiulas, Mobility support through caching in content-based publish/subscribe networks, in 5th International Workshop on Content Delivery Networks (CDN 2010) in conjuction with 10th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid 2010), pp. 715-720, Melbourne, Australia, May 2010.[C.03] Vasilis Sourlas, Georgios S. Paschos, Paris Flegkas and Leandros Tassiulas, Caching in content based publish/subscribe systems, in IEEE Globecom 2009 Next-Generation Networking and Internet Symposium, pp. 1-6, Hawaii, USA, December 2009.[C.02] Vasilis Sourlas, Paris Flegkas, Georgios S. Paschos and Leandros Tassiulas, Distribute, Store and Retrieve Management Policies on Wireless Ad-Hoc Networks using the Content Delivery Publish/Subscribe Paradigm, in proc. of 3rd IEEE Workshop on Autonomic Communications and Network Management - IM 2009 / ACNM 2009, pp 169-176, NY, USA, June 2009.[C.01] Vasilis Sourlas, Paris Flegkas and Leandros Tassiulas, Policy Distribution using the Publish-Subscribe Paradigm for Managing MANETs, in proc. of 11th IFIP/IEEE International Conference on Management of Multimedia and Mobile Networks and Services (MMNS 2008) held as part of Manweek 2008,pp 14-19, Samos, Greece, August 2008.

65Vasilis Sourlas PhD defense 23/7/2013Thank you!!!66Vasilis Sourlas PhD defense 23/7/2013