Dirk Bradler’s research while affiliated with Technical University of Darmstadt and other places

The Internet of Things (IoT) and the Internet of Services (IoS) are two well-known exemplars of the emerging 'Internet variants'. These variants will be tightly interwoven yet specific with respect to the supporting technologies needed. The present paper discusses the five variants identified as essential by the authors: IoT, IoS, Internet-of-Humans, Internet-of-Crowds, and Internet-of-Clouds. For each variant, a non-comprehensive set of research challenges is cited and related to the state of the art and to ongoing projects of the lab.

Gossip‐based epidemic protocols are used to aggregate data in distributed systems. This fault‐tolerant approach neither require maintenance of any global network state nor knowledge of network structure. However, although gossip‐based aggregation algorithms scale well for graphs with good expansion, their efficiency for sparse graphs is unexamined. In this paper, we analyze the feasibility and efficiency of a gossip aggregation protocol in wireless networks with low expansion. We propose a modification of the existing aggregation algorithm for use in locality‐aware, sparse, and static wireless networks. Our protocol terminates autonomously, uses less bandwidth than the original version, and removes the need for the leader election process while counting network nodes. Aggregates are calculated only over nodes placed in the vicinity, and nodes communicate only with their immediate neighbors by using a wireless broadcast. We evaluate our approach by simulation on sparse, irregular graphs with low expansion for the simplified system model. Furthermore, we analytically assess the worst‐case convergence time of this protocol for sparse wireless networks and also for the simplified system model. The proposed protocol can be used in the monitoring and alarming applications in wireless networks. Copyright © 2012 John Wiley & Sons, Ltd.

Topology control for Wireless Sensor Networks (WSN) is a frequently tackled challenge, for which no satisfying general solution for realistic deployments has been found to the current day. Aiding to minimize unnecessary transmissions, it nevertheless represents a crucial function of WSN, in the light of their pursuit of efficiency. kTC is a new WSN topology control that unlike prior art neither relies on location information, nor on complex geometric structures, which could leave doubts about a practical feasibility. Even though location-free approaches have been proposed to circumvent systematic problems, they do not address issues like robustness and adaptability satisfyingly, which may lead to disconnection in real world deployments. kTC is a location-free approach that adapts topologies dynamically in face of changing environmental influences. It is based on a local, pattern-based heuristic, and transmitting only two messages per node to construct the topology it is highly scalable. The graphs kTC creates are symmetric, connected, and planar; they have bounded degree and nodes are θ-separated. Simulative evaluations indicate that kTC outperforms known topology control schemes. A preliminary deployment on a sensor testbed corroborates the obtained results and acts as proof of concept for kTC.

Nodes in mobile networks are usually unevenly distributed over space. Several dense clusters of nodes are interconnected by a few nodes in sparsely occupied areas. Removing vital nodes along such bridges would partition the network and severely reduce the overall connectivity. Consequently, detecting and protecting those few vital nodes is crucial for keeping the network operational. In order to achieve this task, we present our novel approach: BridgeFinder. Most importantly, BridgeFinder allows us to calculate good estimates for global graph measures, while operating as a fully distributed algorithm and causing only very little messaging overhead. It is based on an extended gossiping protocol and is significantly faster and more precise than existing mechanisms. The results of our extensive evaluation show that BridgeFinder is indeed very effective in detecting the few crucial for the network operation nodes.

Topology adaptation is a vital operation in technological networks. It is frequently implemented as either an external process or a distributed online optimization that relies on gathering knowledge on the overall state of the system. In this work we propose MBO, a novel approach that uses network motifs (a local, stochastic metric) for distributed topology optimization of arbitrary, adaptable networks. In order to give a proof of concept we chose to optimize structured Peer-to-Peer overlays towards a fair load balancing. MBO is parametrized using target motif signatures of networks, which are derived from exemplary, generated topologies with the desired properties - a fair load balancing in the demonstrated case. Extensive simulations indicate that for CAN and Kademlia, two different types of P2P systems, MBO leads to a well balanced load, while being minimally intrusive.

Peer-to-Peer networks are divided into two main classes: unstructured and structured. Overlays from the first class are better suited for exhaustive search, whereas those from the second class offer very efficient key-value lookups. In this paper we present a novel overlay, PathFinder, which combines the advantages of both classes within one single overlay for the first time. Our evaluation shows that PathFinder is comparable or even better in terms of lookup and complex query performance than existing peer-to-peer overlays and scales to millions of nodes.

Communication between first responders is vital to the success of large scale disaster management. But communication technologies used by first responders today do not scale well due to heterogeneity, point-to-point connections, and centralized communication structures. As the popularity of devices equipped with Wi-Fi grows, the number of access points (APs) in city centers increases as well. This communication infrastructure exists and should be used in city wide disasters as it is readily available in areas with high population density. In this paper, we investigate Wi-Fi access points in 5 major cities deployed in stores, bars, and restaurants. We want to answer the question if these APs can be used as a mesh networking backbone in disaster response. The main contributions of this paper are (i) the surveyed and analyzed public Wi-Fi layout of five major cities and (ii) the connectivity analysis of the city wide network topology.

Gossip-based epidemic protocols are used to aggregate data in distributed systems. This fault-tolerant approach does neither require maintenance of any global network state nor knowledge of network structure. However, although gossip-based aggregation algorithms scale well for graphs with good expansion, their efficiency for sparse graphs is unexamined. In this paper we analyze the feasibility and efficiency of a gossip aggregation protocol in wireless networks with low expansion. We propose a modification of the existing aggregation algorithm for use in locality-aware, sparse, static wireless networks. Our protocol terminates autonomously, uses less bandwidth than the original version, and removes the need for the leader election process while counting network nodes. Aggregates are calculated only over nodes placed in the vicinity, and nodes communicate only with their immediate neighbors by using a wireless broadcast. We evaluate our approach by simulation on sparse, irregular graphs with low expansion for the simplified system model. Furthermore, we analytically assess the worst-case convergence time of this protocol for sparse wireless networks and also for the simplified system model.

Concise and reliable graph-theoretic analysis of complex networks today is a cumbersome task, consisting essentially of the adaptation of intricate libraries for each specific problem instance. The growing number of complex metrics that have been proposed in the last years, which mainly gain significance due to the increasing computational capabilities at hand, have led to important new insights in the field. However, they have solely been implemented as single algorithms, each specialized for the purpose of calculating exactly the targeted metric for a selected type of network graph. A comprehensive, extensible tool for the concise evaluation of graphs is currently not available. For this purpose we introduce the Graph-Theoretic Network Analyzer (GTNA), an efficient, Java-based toolkit for the comprehensive analysis of complex network graphs. GTNA, while already including the main metrics that are used to analyze the complex networks in computer science today, is simple to extend through a well defined plugin interface for metrics, network descriptions and network generator models. Throughout the paper we present the design and simple extensibility of GTNA, as well as the network models and metrics that are already implemented and give examples of its scalability and performance.