Björn Richerzhagen

Simonstrator: simulation and prototyping platform for distributed mobile applications

The increasing market penetration of mobile devices, such as smartphones and tablets, poses additional challenges on the design of distributed systems. Due to the heterogeneous environment consisting of both, mobile and fixed devices, a multitude of effects on different scales need to be considered. Microscopic effects, such as an individual users interaction with the device, as well as macroscopic effects, such as scalability with the number of users have an impact on the systems performance. The combined evaluation of micro- and macroscopic effects requires both, simulations and prototypical deployments. Furthermore, insights obtained through prototypes during user studies can lead to refined protocols and algorithms, thereby contributing to the overall design process. To enable parallel assessment of micro- and macroscopic effects, we propose the Simonstrator platform, consisting of a lightweight framework for the development and instrumentation of distributed systems as well as runtime environments for (i) the interaction with common simulators, (ii) the deployment on testbeds, and (iii) Android devices. The platform is specifically targeted towards distributed systems for heterogeneous scenarios, considering mobile and fixed networks. We show sample simulations and prototypical deployments of two exemplary use cases: a live video streaming system and a middleware for augmented reality games, highlighting different evaluation goals and environments supported by the proposed Simonstrator platform.

Bypassing the cloud: Peer-assisted event dissemination for augmented reality games

The rising number of mobile devices and their increasing computational capabilities enable new interactive context-sensitive applications. Popular examples are augmented reality games such as Googles Ingress, where users interact with each other in the real world while being part of the game at the same time. This local interaction pattern in the real world as well as in the game is not reflected in the underlying communication pattern. Every locally generated game event is first transferred to a backend server via a cellular connection, from where it is then further disseminated to all players within the given area of interest. This communiation pattern introduces significant delays and limits the interactivity of the game. In this work, we propose an event dissemination system that exploits the locality characteristics of mobile augmented reality games to (i) enable and configure local peer-to-peer dissemination of events when appropriate and (ii) reconfigure or replace the utilized peer-to-peer protocol to adapt to a wide range of requirements. Through extensive evaluation we show that the proposed system decreases the delivery delay by a factor of eight compared to the existing communication pattern, leading to significantly increased information accuracy.

Geodemlia: A robust peer-to-peer overlay supporting location-based search

Existing peer-to-peer overlay approaches for location-based search have proven to be a valid alternative to client-server-based schemes. One of the key issues of the peer-to-peer approach is the high churn rate caused by joining and leaving peers. To address this problem, this paper proposes a new location-aware peer-to-peer overlay termed Geodemlia to achieve a robust and efficient location-based search. To evaluate Geodemlia, a real world workload model for peer-to-peer location-based services is derived from traces of Twitter. Using the workload model, a system parameter analysis of Geodemlia is conducted with the goal of finding a suitable parameter configuration. In addition, the scalability and robustness of Geodemlia is compared to a state-of-the-art tree-based approach by investigating the performance and costs of both overlays under an increasing number of peers, an increasing radius of area searches, an increasing level of churn as well as for different peer placement and search request schemes. The evaluation results reveal that in contrast to the tree-based approach, Geodemlia provides on average a 46% better success ratio as well as a 18% better recall at a moderate higher traffic overhead of 13 bytes/s and an increased average response time of 0.2 s.

PeerfactSim.KOM: Take it back to the streets

Mobile peer-to-peer networks, utilizing ad hoc communication between hand-held communication devices, serve as an alternative to cellular networks for the deployment of applications. To evaluate a new communication mechanism in mobile peer-to-peer network, simulations constitute a useful and frequently applied evaluation technique. Besides initial simulations on plain and empty maps, it is crucial to evaluate if and how the developed communication mechanism performs in the envisioned scenarios dealing with obstacles as well as node mobility. Therefore, this paper introduces a framework that provides two procedures for the creation of arbitrary environments, ranging from simple environments to complex models of cities or regions. Additionally, the framework provides different strategies to model the mobility of nodes. Together with an extended version of PeerfactSim.KOM, a simulation platform is presented that supports the complete workflow for the simulation of mobile P2P networks. The simulation platform provides (i) the modeling of purpose-based environments based on SVG-images, (ii) the modeling of realistic environments based on data from Open Street Map, as well as (iii) synthetic and realistic mobility models.

Adaptive Monitoring for Mobile Networks in Challenging Environments

The increasing capabilities of mobile communication devices are changing the way people interconnect today. Similar trends in the communication technology domain are leading to the expectation that data and media are available anytime and everywhere. A result is an increasing load on communication networks. In dynamic mobile networks that particularly rely on wireless communication such data requirements paired with environmental conditions like mobility or node density increase the risk of network failure. Consequently, monitoring is crucial in mobile networks to ensure reliable and efficient operation. Current monitoring mechanisms mostly rely on a static architecture and exhibit problems to handle the changes of mobile networks and environmental conditions over time. In this paper, an adaptive monitoring mechanism is presented to overcome these limitations. The mechanism exploits the connectivity and resource characteristics of mobile communication devices to (i) reconfigure its monitoring topology and (ii) adapt to changes of mobile networks and environmental conditions. Through evaluations we show that our proposed solution reduces the achieved relative monitoring error by a factor of six and represents a robust and reliable monitoring mechanism for these challenging environments.

Towards the Description and Execution of Transitions in Networked Systems

Today’s distributed systems have to work in changing environments and under different working conditions. To provide high performance under these changing conditions, many distributed systems implement adaptive behavior. While simple adaptation through parameter tuning can only react to a limited range of conditions, a switch between different mechanisms at runtime enables broader adaptivity. However, distributed systems that switch mechanisms at runtime lack a clear abstraction for the adaptive behavior and, thus, usually interleave the adaptation and actual application logic. This leads to complex and error-prone systems that are hard to maintain and not easy to extend.

TOPT: Supporting flash crowd events in hybrid overlay-based live streaming

Recent studies show that an increasing number of over-the-top live streams is delivered over the Internet. For the delivery of those streams, the dynamically changing and potentially large number of users imposes a major challenge. Flash crowds, where the number of users multiplies or significantly drops in a very small time frame, can cause serious degradations in the streaming performance. Due to the missing support for global network-layer multicast, overlay-based approaches have been broadly studied, showing that, with relaxed time constraints, they can scale well with the number of users. Yet, to support flash crowds, scaling has to happen quickly to keep up also with rapidly changing populations. Only a few approaches exist that focus on this aspect by influencing the streaming topology and, so far, it is not clear if and how these mechanisms can be applied to state-of-the-art hybrid streaming systems. Therefore, in this paper, TOPT is proposed, integrating new as well as existing mechanisms in a common framework. The evaluation shows that the streaming topology, indeed, plays a major role during flash crowds. The lightweight and decentralized tree-forming and topology optimization mechanisms of TOPT, combined with tracker extensions to attach new peers in batches, greatly help improving the streaming performance in terms of reduced playback interruptions by more than 60% and slight reduction in communication overhead at an acceptable increase in average startup delays by 24%.

Mind the Gap! Automated Anomaly Detection for Potentially Unbounded Cardinality-Based Feature Models

Feature models are frequently used for specifying variability of user-configurable software systems, e.g., software product lines. Numerous approaches have been developed for automating feature model validation concerning constraint consistency and absence of anomalies. As a crucial extension to feature models, cardinality annotations and respective constraints allow for multiple, and even potentially unbounded occurrences of feature instances within configurations. This is of particular relevance for user-adjustable application resources as prevalent, e.g., in cloud computing. However, a precise semantic characterization and tool support for automated and scalable validation of cardinality-based feature models is still an open issue. In this paper, we present a comprehensive formalization of cardinality-based feature models with potentially unbounded feature multiplicities. We apply a combination of ILP and SMT solvers to automate consistency checking and anomaly detection, including novel anomalies, e.g., interval gaps. We present evaluation results gained from our tool implementation showing applicability and scalability to larger-scale models.

Transition-enabled event dissemination for pervasive mobile multiplayer games

Todays smartphones feature sophisticated computational capabilities as well as a plethora of sensors, enabling new kinds of applications. One popular example are pervasive mobile multiplayer games, where interactions with other users or physical objects in the real world are part of the gameplay. This induces a notion of locality, as a users actions affect other nearby users. However, this locality in the interaction is not reflected in the underlying communication system. Events triggered by users are sent via the cellular connection to a remote data center, where they are processed and then distributed to other players, again via the cellular link. In this work, we demonstrate an event dissemination system that utilizes the available local communication interfaces of todays smartphones to distribute events in groups of nearby players. The system executes transitions between different communication interfaces (e.g., Bluetooth or Wi-Fi Direct) and the utilized dissemination protocol depending on the size and density of the group of players, thereby exploiting the characteristics of the chosen interface. Attendees can experience the resulting benefits in terms of latency and update frequency by playing our mobile pervasive multiplayer game TowerWorld at the venue.

Seamless Transitions between Filter Schemes for Location-Based Mobile Applications

With a plethora of sensors and ubiquitous access to the Internet, modern smartphones have enabled a broad range of context-based applications. Most applications make use of the users physical location to filter relevant content. However, filtering based on dynamic contextual information results in high complexity of the filtering process. This limits the applicability of existing publish/subscribe systems, as they rely on aggregation of filters and fast decentralized matching and forwarding. In this work, we propose a mechanism for transitions between different filter schemes for location-based services. Our mechanism adapts the filtering process to the dynamics in user behavior and resulting load by trading computational complexity at the broker against communication overhead and computational complexity at the mobile client. We integrate our mechanism into an existing publish/subscribe system and evaluate transitions between a context-based filter scheme and two channel-based filter schemes, showing the applicability of our approach.