Information-Centric Network (ICN) architectures, such as Named Data Networking (NDN), can improve content delivery on the Internet by deploying in-network caching techniques. Replacing the entire established Internet with a novel architecture is a non-trivial task, which is why this work develops a layered network architecture consisting of several smaller NDN-based mobile networks (resp., domains), interconnected using a Distributed Hash Table (DHT)-based network running as an overlay on top of existing Internet infrastructures. Using simulations, we model real-world network characteristics to evaluate the proposed architecture’s performance successfully.

A service-centric network requires a routing protocol to route service requests towards service providers. Routing operations can be divided into intra-domain and inter-domain routing. In the proposed approach, a so-called supernode is responsible for managing its own domain as well as for communicating with the supernodes of other domains to perform inter-domain routing. In order to appoint appropriate nodes as supernodes in the network topology, in this paper, we use Dominating Sets (DS) and Connected Dominating Sets (CDS). We propose fully distributed algorithms for constructing DS as well as CDS over the network topology. To prepare routing information, the nodes of each domain inform their supernodes about their available service names and resources (e.g., CPU, RAM). To this aim, the nodes use Bloom filters which reduce bandwidth and storage overhead. The performance evaluation shows that the required bandwidth overhead for DS and CDS construction algorithms increases with the topology size. The results also show that for large network topologies, CDS-based routing requires significantly less bandwidth overhead than both DS-based routing and Named Data Networking with multicast forwarding strategy. Finally, from the results we can observe that both DS-based and CDS-based routing have significantly lower service retrieval time than NDN multicast strategy.

L-SCN is a two-layered Service-Centric Networking (SCN) architecture. The L-SCN design splits the network into domains and specifies communication protocols for service provider information propagation. Nodes in a domain receive substantial knowledge about the available resources (e.g., CPU, RAM) and available services within the domain, while the communication between different domains is realized through supernodes. We extend L-SCN with new communication mechanisms, which improve the processing time and provide lower protocol overhead for service request processing. The two proposed mechanisms are named event-driven and provider-driven. The event-driven mechanism propagates service provider information based on an event (e.g., high overload). The provider-driven mechanism propagates service provider information periodically.

Service-Centric Networking (SCN) is a Future Internet architecture extending ICN with support for services, in which addressing and routing centers around services. SCN provides session support, however, recovery mechanisms do not exist in SCN session management. Therefore, SCN sessions suffer from link and node failures. In this paper, we present the design, implementation, and evaluation of three link failure recovery techniques for sessions in SCN. The first mechanism is based upon propagating session identifiers within the network using Bloom filters, the second design is based upon the propagation of service provider identifiers, and the third design uses piggy-backing for the propagation of service provider identifiers.

This paper presents and evaluates the first open-source Network Function Virtualization (NFV)/Software Defined Networking (SDN)-based Mobile Edge Computing (MEC) platform. Our platform solves the Mobile Edge (ME) management issues with respect to Application (App) provisioning and traffic management. First, the ME Apps are managed as Virtual Network Functions (VNFs) on top of the virtual environment through the Juju VNF Manager (VNFM). Second, we develop an SDN controller to manage traffic on the ME System. Third, unlike other relevant architectures of ME systems, we use the control plane (i.e., S1 interface) to derive appropriate states for traffic management. Finally, we evaluate our solution in two use-cases: ME caching and Information Centric (ICN)/Delay Tolerant (DTN) Public Safety communication (PS). The MEC caching framework displays improved user Quality of Experience, e.g., latency, in comparison to direct communication, while the PS solution provides a residual mean of communication for rescue teams, when the network core (EPC) and a Public Data Network (PDN) are unavailable.

Service-Centric Networking (SCN) is a future Internet paradigm derived from Information-Centric Networking (ICN). SCN extends the ICN paradigm with service support. In SCN, services are the key component of the network. In this paper, we design a novel intra-domain routing architecture by integrating an extended version of the Named-data Link State Routing (NLSR) protocol into SCN. We make use of NLSR to disseminate service provider prefixes and resource availability information within the intra-domain network. The resource availability information allows nodes in the intra-domain network to label faces for future forwarding decisions. Our design supports short and long types of service input. We have implemented and evaluated our design against existing schemes through simulations.

Service-Centric Networking (SCN) is a concept derived from Information-Centric Networks (ICN). In SCN, the service is in the center of the architectural design. Current efforts of SCN focus on design enhancements and the derivation of new components providing new functionality. In this article, we present session support for services in SCN. Our design makes use of existing hierarchical naming schemes to specify sessions using unique session identifiers. Sessions are established through a two-way handshake, which allows both the service consumer and provider to exchange their generated unique session identifiers. We have implemented and evaluated our SCN service session support mechanism, which provides promising results.

In this paper, we present L-SCN, a new routing architecture for Service-Centric Networking (SCN), which makes use of a two-layer forwarding scheme composed of inter-domain and intra-domain communication. Unlike existing SCN routing architectures relying on a flat organization, our design splits the network into domains. Nodes within a domain possess significant knowledge about existing services and available resources within the domain. Supernodes provide a significant advantage in comparison to other architectures. They assure the inter-domain communication and make use of a pull and push mechanism combined with Bloom filters. It allows us to minimize the protocol overhead and optimize sharing of information about available services and resources in the network.

In this paper we present BitWorker, a platform for community distributed computing based on BitTorrent. Any splittable task can be easily specified by a user in a meta-information task file, such that it can be downloaded and performed by other volunteers. Peers find each other using Distributed Hash Tables, download existing results, and compute missing ones. Unlike existing distributed computing schemes relying on centralized coordination point(s), our scheme is totally distributed, therefore, highly robust. We evaluate the performance of BitWorker using mathematical models and real tests, showing processing and robustness gains. BitWorker is available for download [1] and use by the community.