Showing papers by "Hannes Hartenstein published in 2014"

Inter-vehicle communication: Quo vadis

Abstract: In September 2013, leading experts in intervehicle communication from all over the world met at the renowned Dagstuhl Castle for a seminar discussing the question "Inter-Vehicular Communication - Quo Vadis?" The objective was to identify the current state of the art and, more important, the open challenges in R&D from both a scientific and an industrial point of view. After more than a decade of research on vehicular networks, the experts very seriously asked whether additional research in this field is necessary and, if so, which will be the most intriguing and innovative research directions. It turned out that the overall perspective has changed in the last few years, mainly as a result of the ongoing field operational tests in the United States and Europe. In this article, we report the key outcomes and results from the discussions, pointing to new research directions and new challenges that need to be met for a second generation of vehicular networking applications and protocols. In particular, we present the reports and findings from the four working groups on scientific foundations of vehicular networking, field operational tests, IVC applications, and heterogeneous vehicular networks.

Designing fail-safe and traffic efficient 802.11p-based rear-end collision avoidance

Abstract: An essential, but nevertheless often neglected, objective for the design of safety-critical IEEE 802.11p-based application is: fail-safety. A fail-safe application is an application that incorporates features that automatically counteract the effect of anticipated sources of failure. In the context of a rear-end collision avoidance application two main possible sources of failure exist: an unpredictable human behavior and unreliable communication. This paper presents mechanisms that, when integrated into the design of rear-end collision avoidance application, counteract these failure cases and thus ensure fail-safety. However, fail-safety comes at a cost: either large inter-vehicle distances have to be kept to ensure that all drivers have enough time to react or the application has to take over vehicle control to allow smaller inter-vehicle distances and thus higher traffic efficiency. In this paper we analyze this tradeoff and quantify what part of drivers' population has to be deprived of vehicle control in order to achieve acceptable traffic efficiency when deploying IEEE 802.11p-based rear-end collision avoidance application.

Exploiting the parallelism of large-scale application-layer networks by adaptive GPU-based simulation

Abstract: We present a GPU-based simulator engine that performs all steps of large-scale network simulations on a commodity many-core GPU. Overhead is reduced by avoiding unnecessary data transfers between graphics memory and main memory. On the example of a widely deployed peer-to-peer network, we analyze the parallelism in large-scale application-layer networks, which suggests the use of thousands of concurrent processor cores for simulation. The proposed simulator employs the vast number of parallel cores in modern GPUs to exploit the identified parallelism and enables substantial simulation speedup. The simulator adapts its configuration at runtime in order to balance parallelism and overheads to achieve high performance for a given network model and scenario. A performance evaluation for simulations of networks comprising up to one million peers demonstrates a speedup of up to 19.5 compared with an efficient sequential implementation and shows the effectiveness of the runtime adaptation to different network conditions.

Inter-vehicle Communication: Quo Vadis. Report from Dagstuhl Seminar 13392

Abstract: "Inter-Vehicular Communication - Quo Vadis?" With this question in mind, leading experts in the field of vehicular networking met in Dagstuhl to discuss the current state of the art and, most importantly, the open challenges in R&D from both an scientific and an industry point of view After more than a decade of research on vehicular networks, the experts very seriously asked the question whether all of the initial research issues had been solved so far It turned out that the perspective changed in the last few years, mainly thanks to the ongoing field operational tests in Europe and the US The results point to new research directions and new challenges that need to be solved for a second generation of vehicular networking applications and protocols In four working groups, the experts studied these new challenges and derived recommendations that are also very helpful for the respective funding organizations

Inter-Vehicular Communication -- Quo Vadis (Dagstuhl Seminar 13392)

Abstract: "Inter-Vehicular Communication -- Quo Vadis?". With this question in mind, leading experts in the field of vehicular networking met in Dagstuhl to discuss the current state of the art and, most importantly, the open challenges in R&D from both an scientific and an industry point of view. After more than a decade of research on vehicular networks, the experts very seriously asked the question whether all of the initial research issues had been solved so far. It turned out that the perspective changed in the last few years, mainly thanks to the ongoing field operational tests in Europe and the U.S. The results point to new research directions and new challenges that need to be solved for a second generation of vehicular networking applications and protocols. In four working groups, the experts studied these new challenges and derived recommendations that are also very helpful for the respective funding organizations.

Parallelism potentials in distributed simulations of Kademlia-based peer-to-peer networks

Abstract: The benefits of distributing a network simulation depend on characteristics of the simulated network. Performance improvements reported in the literature are comparatively low for peer-to-peer overlay networks in particular, as the logical topology of these networks can necessitate frequent synchronization between the processors executing the simulation. In this paper, we show that a speedup of up to a factor of 6.0 using 16 nodes connected using InfiniBand and close to linear reductions in memory usage are possible for simulations of Kademlia-based networks. Our distributed simulator implementation enables simulations of one of the largest peer-to-peer networks at full scale of about 10 million peers. Based on the two fundamental goals of minimizing communication between processors and minimizing synchronization overheads, we propose two strategies for assigning simulated nodes to processors. We analyze the effects of the two strategies and show that each strategy supports one of the goals, while being detrimental to the other. We propose efficiency metrics that expose how much of the potential for parallel execution is exploited by a simulator. Through detailed performance measurements and by applying the new metrics to our simulator implementation, we quantify remaining efficiency potentials.

bwIDM – Federated Access to IT-Based Services at the Universities of the State of Baden-Württemberg

Abstract: The use and provisioning of services across organizations has not only gained momentum in the business web, but also in academic environments. For instance, in the state of Baden-Wurttemberg, national and state-funded cluster computing resources, operated by a single university, have to be accessible by the users of other universities as well. Two avoid that users have to create and maintain dedicated accounts at each organization, the concept of federated identity management (FIM) can be applied. FIM allows users to use a single identity at their home organization to access services that are operated by other organizations. In this paper, we survey major requirements that need to be considered when establishing such a federation and its technical platform. Furthermore, we show how the bwIDM project established a FIM platform for the state of Baden-Wurttemberg that matches the requirements and that is based on the Security Assertion Markup Language (SAML) standard. In particular, we outline bwIDMs approach on how to integrate non web-based services with SAML federations.

Understanding differences in MAC performance

Abstract: The suitability and performance of medium access protocols in vehicular environments is already being investigated over a long period of time. Carrier Sense Multiple Access (CSMA) has been shown to perform sufficiently well in most situations and being able to support safety and efficiency vehicular applications. Recently, Self-organizing Time-Division Multiple Access (STDMA) is being considered as an alternative and has been shown to coordinate the channel slightly better under certain situations. However, when comparing both protocols the precise details of radio and network conditions and parametrization of the protocols are decisive on which protocol takes a slight lead. Consequently, scenarios can be constructed quite easily in which one protocol is superior over the other one. The focus of this work is thus not to absolutely compare both protocols, but rather to understand the strengths and weaknesses of both protocols in certain situations. In particular, we consider i) to which degree hidden nodes influence the coordination ability, ii) how an extended carrier sensing range is beneficial and iii) how temporary fading influences the performance of both MAC protocols. Our results show that while an extended carrier sensing range is only beneficial for CSMA, the existence and severity of fading is far less detrimental for STDMA than for CSMA.

SECURUS: Composition of Confidentiality Preserving Indexing Approaches for Secure Database-as-a-Service

Abstract: The Database-as-a-Service (DaaS) paradigm addresses the outsourcing of databases to specialized storage providers, potentially reducing costs and increasing robustness. A common DaaS requirement is to prevent the storage provider from retrieving information from the outsourced data while still allowing it to execute queries. Various confidentiality preserving indexing approaches (CPIs) have been proposed that preserve confidentiality while allowing the SP to participate in query execution. However, these approaches only allow the execution of specific kinds of queries, for instance queries that select records based on the equality of a certain attribute to a search term. Choosing an optimal set of CPIs that matches the users specific requirements is a hard task, as it requires expert knowledge about both the scenario and the available CPIs. In this article, we provide an overview of the Securus framework [10] that tackles this issue. Securus allows the user to define her confidentiality needs and query workload in a Policy Profile. Securus then computes a set of CPIs that matches the specified requirements. Furthermore, a software adapter called Mediator is generated that implements the chosen CPIs and can be used to seamlessly outsource and query data.

Self-optimization of DHT lookups through run-time performance analysis

Abstract: Distributed Hash Tables (DHTs) provide information lookup within a Peer-to-Peer (P2P) network. A multitude of distributed applications leverages DHTs for offering more advanced services such as distributed file systems, web caches or distributed DNS. For such DHT-based applications, lookup performance is highly important. However, lookup performance is severely affected by network characteristics, i.e., churn and connectivity issues due to NAT routers. As those characteristics are heavily influenced by user behavior, changes are not only likely but also hard to predict. Although DHTs are known for their self-organization, current implementations often do not adapt optimally to variation in network characteristics. In this paper, we propose to dynamically optimize the client through tuning its parameters at run-time. For doing so, different configurations are tested and compared automatically. To reduce overhead, requests sent to other peers are recorded and replayed by a simulation engine, if the same peer is queried again using the same parameter. We evaluated our approach at two exemplary scenarios of the future state of the BitTorrent Mainline DHT (MDHT), one of the most widely used public DHTs. In these scenarios, the lookups of a client using static parameters were more than three times slower and had a 25% higher network overhead than those of an adaptive client. With only 4 additional UDP packets sent per second and a one-digit CPU load, the proposed approach also induces minimal overhead.

Index Optimization for L-Diversified Database-as-a-Service

Abstract: Preserving the anonymity of individuals by technical means when outsourcing databases to semi-trusted providers gained importance in recent years. Anonymization approaches exist that fulfill anonymity notions like \(\ell \)-diversity and can be used to outsource databases. However, indexes on anonymized data significantly differ from plaintext indexes both in terms of usage and possible performance gains. In most cases, it is not clear whether using an anonymized index is beneficial or not.

Appropriate selection of urban vehicle-to-vehicle radio propagation models

Abstract: Urban vehicle-to-vehicle radio propagation is commonly modeled using simplified path loss models which are either based on empirical measurements or analytical considerations These models have in common that their parameterability is rather limited and it is thus only possible to consider, eg, the distance between transmitter and receiver, antenna heights or street widths Aspects, such as the shape of an intersection or to which degree vehicles or vegetation are present cannot explicitly be considered using these models In contrast, recent work suggests that even effects, such as obstructed line-of-sight by vehicles on the road or destructive multipath propagation can drastically influence simulation results Accordingly, adjusted models are suggested which, however, incorporate only one additional aspect at a time In this paper, we pursue a different approach and take a first step in evaluating which aspects influence radio conditions in urban areas to which degree and how these individual aspects affect each other We consequently consolidate existing works and evaluate in which situations a more detailed radio propagation modeling might yield substantially different results with respect to the requirements of IEEE 80211p networks In order to achieve comparable results and being able to model several aspects, we employed ray tracing with an accurate geographic scenario and individually modeled obstacles, such as post boxes or trees at the roadside Our results show and explain that the presence of radio obstacles can indeed make a difference within certain ranges if considered individually, the overall path loss in a heterogeneous and crowded urban scenario, however, is still approximated well with currently employed path loss models

Technologies—Communication: Wireless LAN‐Based Vehicular Communication

Abstract: Wireless local area networking (WLAN)-based communication enables vehicles to exchange information that is beyond the vehicle's and the driver's direct perception. It has the potential to support various applications for road safety and traffic efficiency, such as road hazard warning and collision avoidance. As opposed to cellular mobile networks, WLAN-based vehicular communication does not require a central control or an operator; instead it uses a decentralized and self-organizing approach. This article introduces key requirements and basic characteristics of WLAN-based vehicular communication and outlines the system architecture. Furthermore, it gives an overview of the most important technology components for WLAN-based vehicular communication, covering radio and communication protocols, security and privacy, radio resource management, and congestion control. The article concludes with an overview about standardization and an outlook on the system deployment. Keywords: car-to-X communication; vehicular ad hoc networks; dedicated short-range communication; cooperative systems; vehicular area network; inter-vehicular communications; intelligent transportation systems

Spoilt for choice: graph-based assessment of key management protocols to share encrypted data

Abstract: Sharing data with client-side encryption requires key management. Selecting an appropriate key management protocol for a given scenario is hard, since the interdependency between scenario parameters and the resource consumption of a protocol is often only known for artificial, simplified scenarios. In this paper, we explore the resource consumption of systems that offer sharing of encrypted data within real-world scenarios, which are typically complex and determined by many parameters. For this purpose, we first collect empirical data that represents real-world scenarios by monitoring large-scale services within our organization. We then use this data to parameterize a resource consumption model that is based on the key graph generated by each key management protocol. The preliminary simulation runs we did so far indicate that this key-graph based model can be used to estimate the resource consumption of real-world systems for sharing encrypted data.

Index Optimization for L-Diversified Database-as-a-Service.

Abstract: Preserving the anonymity of individuals by technical means when outsourcing databases to semi-trusted providers gained importance in recent years. Anonymization approaches exist that fulfill anonymity notions like \(\ell \)-diversity and can be used to outsource databases. However, indexes on anonymized data significantly differ from plaintext indexes both in terms of usage and possible performance gains. In most cases, it is not clear whether using an anonymized index is beneficial or not.

From implicit to explicit knowledge: a tool for preserving and sharing mental links in science

Abstract: In this paper we propose MentaLink, a tool for preserving and sharing mental links in science. MentaLink is intended as a public knowledge base of links between scientific publications. Contributors can collaboratively define and edit links between entire articles or specific text passages. MentaLink builds on the idea of typed links, allowing authors to explicitly specify how the publications relate to each other, e.g., whether they share the problem statement, whether one publication is built on another or whether they contain contradictory results.