2021, Scherb, Christopher, Bürklin, Pascal, Tschudin, Christian

Nowadays, most network systems are based on fixed and reliable infrastructure, but with Internet of Things (IoT), smart home and smart city systems are used more and more in mobile scenarios and vehicles become connected. Often low power mobile devices are supported by cloud computing capabilities. However, infrastructure may not be available everywhere, where mobile devices are used and local information is often only required locally, thus do not need to be uploaded into the cloud. SCoIoT is based on novel Information Centric Networking communication pattern and is designed to support cooperative computations without requiring new infrastructure or even in absence of infrastructure due to the device to device communication pattern. Thereby, nodes voluntarily participate in computations and help to spread the computation to enable further nodes to participate in the computation and to share the results. SCoIoT utilizes Append-only-Log technology for synchronization and verification of requests and results.

2019, Scherb, Christopher, Marxer, Claudio, Tschudin, Christian

Information Centric Networking (ICN) is a modern networking concept which enables users to address named data directly by their name, without knowing the location where the data is stored. Since requesting static data is only a special case of requesting processed data, Named Function Networking (NFN) is a generalization of ICN by providing the possibility to define how data should be processed before they are delivered. Thereby, the network decides, where to process the data. The decision where to process data is crucial for the performance and the load on the network, especially when NFN is used within a data center. In this paper we discuss how NFN forwarding decisions can be improved and how to plan an execution of a computation in a name-based network to improve the execution performance. A plan is a list of instruction how and where to execute a computation. To create a plan, the network finds the best way to execute a computation regarding to a predefined metric. Furthermore, we present an extension for reusing plans and creating templates.

2021, Scherb, Christopher, Grewe, Dennis, Tschudin, Christian

Today's Internet is heavily used for multimedia streaming from cloud backends, while the Internet of Things (IoT) challenges the traditional data flow, with high data volumes produced at the network edge. Information Centric Networking (ICN) advocates against a host-centric communication model using content identifiers decoupling content from a location, and therefore, promising for distributed edge computing environments. However, the resulting coupling of data to content identifiers in ICNs introduces new challenges regarding dissemination of large data volumes and services and synchronization across multiple consumers. We present Tangle Centric Networking (TCN) - a decentralized data structure for coordinated distribution of data and services for ICN deployments. TCN simplifies the management of data and service changes and updates them accordingly in network nodes using principles of Tangles. Using simulations, first implementations of TCN show improvements in data discovery as well as less synchronization overhead of large volumes of data compared to a state-of-the-art ICN system.

2018, Grewe, Dennis, Marxer, Claudio, Scherb, Christopher, Wagner, Marco, Tschudin, Christian

Recently, vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) connectivity transitioned from a vision of the future to reality. Applications in such environments vary from local propagation of road conditions to large-scale traffic flow control systems. In this demo, we present a network stack for the data exchange in the automotive IoT, based on the Named Function Networking (NFN) principles. In NFN, the communication model is not restricted to propagation of static data but natively supports computation-offloading to other nodes. We present solutions and report on experiments with real cars on a test course.

2019, Scherb, Christopher, Emde, Samuel, Marxer, Claudio, Tschudin, Christian

Limited energy capacity and computation power is a common characteristic of mobile but connected devices. Edge computing, i.e. outsourcing computation task to close-by stationary service providers, is a widespread approach to still deploy computation-intensive applications on such devices. However, if moving at high speed (like for instance vehicles or trains), the contact time with network access points are very short (in the range of 3-5sec). Based on this fact, we identify the two challenging situations which are expected to happen very frequently and therefore should be considered when designing the communication system's architecture: (a) A client is connected via different network access points when scheduling a computation and when the result is ready for delivery. (b) A client's network access point changes (potentially several times) while uploading computation arguments or downloading computation results. In this paper, we pursue an information-centric and named-function networking approach to tackle these challenges.

2018, Scherb, Christopher, Grewe, Dennis, Marxer, Claudio, Tschudin, Christian

Named Function Networking (NFN) is an extension for Information Centric Networking (ICN) to execute computation inside the Network. Thereby, NFN consists of two contributions: A workflow definition and a resolution strategy. The ICN communication model enables NFN to reuse already computed results by using the network's content store. To resolve a computation, NFN first tries to find a cached result and only if no result was found, the computation is executed - so-called FoX (Find or Execute) resolution strategy. Initially, NFN was optimized for cloud computing and data center computing next to the big data objects. However, new trends like IoT and edge computing describe other requirements to network computations (e.g. dynamic computations of automotive services at the edge). In this paper, we explore how the resolution strategy can be modified to fit to IoT scenarios without changing the workflow definition. Based on two exemplary IoT use cases (home automation and automotive IOT), new resolution strategies will be presented.