Ioannis Psaras

Probabilistic in-network caching for information-centric networks

In-network caching necessitates the transformation of centralised operations of traditional, overlay caching techniques to a decentralised and uncoordinated environment. Given that caching capacity in routers is relatively small in comparison to the amount of forwarded content, a key aspect is balanced distribution of content among the available caches. In this paper, we are concerned with decentralised, real-time distribution of content in router caches. Our goal is to reduce caching redundancy and in turn, make more efficient utilisation of available cache resources along a delivery path. Our in-network caching scheme, called ProbCache, approximates the caching capability of a path and caches contents probabilistically in order to: i) leave caching space for other flows sharing (part of) the same path, and ii) fairly multiplex contents of different flows among caches of a shared path. We compare our algorithm against universal caching and against schemes proposed in the past for Web-Caching architectures, such as Leave Copy Down (LCD). Our results show reduction of up to 20% in server hits, and up to 10% in the number of hops required to hit cached contents, but, most importantly, reduction of cache-evictions by an order of magnitude in comparison to universal caching.

Modelling and evaluation of CCN-caching trees

Networking Named Content (NNC) was recently proposed as a new networking paradigm to realise Content Centric Networks (CCNs). The new paradigm changes much about the current Internet, from security and content naming and resolution, to caching at routers, and new flow models. In this paper, we study the caching part of the proposed networking paradigm in isolation from the rest of the suggested features. In CCNs, every router caches packets of content and reuses those that are still in the cache, when subsequently requested. It is this caching feature of CCNs that we model and evaluate in this paper. Our modelling proceeds both analytically and by simulation. Initially, we develop a mathematical model for a single router, based on continuous time Markov-chains, which assesses the proportion of time a given piece of content is cached. This model is extended to multiple routers with some simple approximations. The mathematical model is complemented by simulations which look at the caching dynamics, at the packet-level, in isolation from the rest of the flow.

Cache less for more in information-centric networks

Ubiquitous in-network caching is one of the key aspects of information-centric networking (ICN) which has recently received widespread research interest. In one of the key relevant proposals known as Networking Named Content (NNC), the premise is that leveraging in-network caching to store content in every node it traverses along the delivery path can enhance content delivery. We question such indiscriminate universal caching strategy and investigate whether caching less can actually achieve more . Specifically, we investigate if caching only in a subset of node(s) along the content delivery path can achieve better performance in terms of cache and server hit rates. In this paper, we first study the behavior of NNCs ubiquitous caching and observe that even naive random caching at one intermediate node within the delivery path can achieve similar and, under certain conditions, even better caching gain. We propose a centrality-based caching algorithm by exploiting the concept of (ego network) betweenness centrality to improve the caching gain and eliminate the uncertainty in the performance of the simplistic random caching strategy. Our results suggest that our solution can consistently achieve better gain across both synthetic and real network topologies that have different structural properties.

Cache less for more in information-centric networks (extended version)

Ubiquitous in-network caching is one of the key aspects of information-centric networking (ICN) which has received widespread research interest in recent years. In one of the key relevant proposals known as Content-Centric Networking (CCN), the premise is that leveraging in-network caching to store content in every node along the delivery path can enhance content delivery. We question such an indiscriminate universal caching strategy and investigate whether caching less can actually achieve more. More specifically, we study the problem of en route caching and investigate if caching in only a subset of nodes along the delivery path can achieve better performance in terms of cache and server hit rates. We first study the behavior of CCNs ubiquitous caching and observe that even naive random caching at a single intermediate node along the delivery path can achieve similar and, under certain conditions, even better caching gain. Motivated by this, we propose a centrality-based caching algorithm by exploiting the concept of (ego network) betweenness centrality to improve the caching gain and eliminate the uncertainty in the performance of the simplistic random caching strategy. Our results suggest that our solution can consistently achieve better gain across both synthetic and real network topologies that have different structural properties. We further find that the effectiveness of our solution is correlated to the precise structure of the network topology whereby the scheme is effective in topologies that exhibit power law betweenness distribution (as in Internet AS and WWW networks).

Curling: Content-ubiquitous resolution and delivery infrastructure for next-generation services

CURLING, a Content-Ubiquitous Resolution and Delivery Infrastructure for Next Generation Services, aims to enable a future content-centric Internet that will overcome the current intrinsic constraints by efficiently diffusing media content of massive scale. It entails a holistic approach, supporting content manipulation capabilities that encompass the entire content life cycle, from content publication to content resolution and, finally, to content delivery. CURLING provides to both content providers and customers high flexibility in expressing their location preferences when publishing and requesting content, respectively, thanks to the proposed scoping and filtering functions. Content manipulation operations can be driven by a variety of factors, including business relationships between ISPs, local ISP policies, and specific content provider and customer preferences. Content resolution is also natively coupled with optimized content routing techniques that enable efficient unicast and multicast- based content delivery across the global Internet.

Hash-routing schemes for information centric networking

Hash-routing has been proposed in the past as a mapping mechanism between object requests and cache clusters within enterprise networks. In this paper, we revisit hash-routing techniques and apply them to Information-Centric Networking (ICN) environments, where network routers have cache space readily available. In particular, we investigate whether hash-routing is a viable and efficient caching approach when applied outside enterprise networks, but within the boundaries of a domain. We design five different hash-routing schemes which efficiently exploit in-network caches without requiring network routers to maintain per-content state information. We evaluate the proposed hash-routing schemes using extensive simulations over real Internet domain topologies and compare them against various on-path caching mechanisms. We show that such schemes can increase cache hits by up to 31% in comparison to on-path caching, with minimal impact on the traffic dynamics of intra-domain links.

In-Network Cache Management and Resource Allocation for Information-Centric Networks

We introduce the concept of resource management for in-network caching environments. We argue that in Information-Centric Networking environments, deterministically caching content messages at predefined places along the content delivery path results in unfair and inefficient content multiplexing between different content flows, as well as in significant caching redundancy. Instead, allocating resources along the path according to content flow characteristics results in better use of network resources and therefore, higher overall performance. The design principles of our proposed in-network caching scheme, which we call ProbCache, target these two outcomes, namely reduction of caching redundancy and fair content flow multiplexing along the delivery path. In particular, ProbCache approximates the caching capability of a path and caches contents probabilistically to: 1) leave caching space for other flows sharing (part of) the same path, and 2) fairly multiplex contents in caches along the path from the server to the client. We elaborate on the content multiplexing fairness of ProbCache and find that it sometimes behaves in favor of content flows connected far away from the source, that is, it gives higher priority to flows travelling longer paths, leaving little space to shorter-path flows. We introduce an enhanced version of the main algorithm that guarantees fair behavior to all participating content flows. We evaluate the proposed schemes in both homogeneous and heterogeneous cache size environments and formulate a framework for resource allocation in in-network caching environments. The proposed probabilistic approach to in-network caching exhibits ideal performance both in terms of network resource utilization and in terms of resource allocation fairness among competing content flows. Finally, and in contrast to the expected behavior, we find that the efficient design of ProbCache results in fast convergence to caching of popular content items.

Deep-Space Transport Protocol: A novel transport scheme for Space DTNs

The Delay-/Disruption-Tolerant Networking Architecture calls for new design principles that will govern data transmission and retransmission scheduling over challenged environments. In that context, novel routing, transport and application layer algorithms have to be established in order to achieve efficient and reliable communication between DTN-nodes. In this study, we focus on the evolution of the terrestrial Internet into the Interplanetary or Space Internet and propose adoption of the Deep-Space Transport Protocol (DS-TP) as the transport layer scheme of choice for the space networking protocol stack. We present DS-TPs basic design principles and we evaluate its performance both theoretically and experimentally. We verify that practice conforms with theory and observe great performance boost, in terms of file delivery time between DTN-nodes, in case of DS-TP. In particular, the gain of DS-TP against conventional proposals for deep-space communications increases with the link error rate; under conditions DS-TP can improve the performance of the transport layer protocol by a factor of two (i.e., DS-TP can become two times faster than conventional protocols).

Name-Based Replication Priorities in Disaster Cases

In the immediate aftermath of a natural disaster, network infrastructure is likely to have suffered severe damages that challenge normal communications. In addition to that, traffic substantially increases as a result of people attempting to get in touch with friends, relatives or the rescue teams. To address such requirements of a challenged network, we propose a communication framework based on messages that exploits name-based replication of content and enables ad-hoc communications with spatial and temporal scoping and prioritisation of named messages. We evaluate our design against less sophisticated replication strategies and show that important messages (e.g., from first responders) get disseminated to more nodes than less important messages.

DS-TP: Deep-Space Transport Protocol

We present deep-space transport protocol (DS- TP), a new reliable protocol for deep-space communication links. DS-TPs main advantage is its ability to complete file transfers faster than conventional TCP, SCPS-TP and Saratoga. Therefore, missions with small connectivity time are greatly favored. Deep space communication links are characterized by long propagation delays, high BERs, intermittent connectivity (i.e., blackouts) and bandwidth asymmetries. Common approaches to deal with the above unique characteristics are: rate-based, open-loop protocols to deal with huge propagation delays; regular retransmissions to deal with high BERs; transmission suspension to deal with blackouts; SNACKs to deal with bandwidth asymmetries. We adopt some of the above approaches, namely, the open-loop, rate-based transmission and the SNACKs and focus on the optimization of the rest, namely, the retransmission strategy of the transport protocol to deal either with high BERs or with blackouts. More precisely, DS-TP includes the Double Automatic Retransmission (DAR) technique. DAR sends each packet twice, importing some intentional delay (Rd) between the original transmission and the retransmission. Therefore, in the presence of communication gaps (i.e., errors or blackouts), corrupted packets will eventually be replaced by the same correct packets that arrive with delay Rd. Rd, however, is much smaller than the traditional TCP-RTO value. Our theoretical performance evaluation results reveal that DS-TP presents high potential for deploy ability. In particular, we show that for PER=50%, DS-TP completes a file transfer in half time of a conventional protocol.