Nils Richerzhagen

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.

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.

The human factor: A simulation environment for networked mobile social applications

Networked mobile social applications are becoming increasingly popular with Pokemon Go being a recent example. These applications focus on direct interaction between mobile users within close proximity. As a result, tailored communication systems have been proposed to exploit the resulting locality properties by augmenting typical cloud-based application infrastructures with local ad hoc communication. However, evaluating these communication systems is challenging: (i) client mobility heavily influences interaction and, thus, the resulting workload; (ii) a multitude of connectivity models needs to be considered for direct ad hoc communication, cellular networks, and potential Wi-Fi offloading scenarios. Consequently, we present a set of human mobility models, interaction models for networked social applications, and communication models to ease the creation of these surrounding heterogeneous scenarios for the considered communication systems. We integrate these models into a common simulation and prototyping environment, bridging the gap between mobility and network simulation and allowing the combined study of human-centric and network-centric effects. We show the applicability and resulting insights of our proposed models for two case studies: a mobile augmented reality game and a monitoring service utilizing multi-dimensional offloading.

Stateless Gateways - Reducing Cellular Traffic for Event Distribution in Mobile Social Applications

The increasing capabilities of modern smartphones lead to the design of mobile social applications focusing on direct interaction between users. Ranging from mobile social networks to fully-fledged augmented reality games, these applications usually operate on contextual information to identify relevant content - most notably, the users physical location. The resulting locality properties of the interaction between users are not well reflected by the cloud-based, centralized infrastructure utilized in todays mobile applications. Thus, data that is relevant to a group of nearby users is downloaded multiple times via the cellular network. Due to capped and/or expensive data tariffs, this can have severe impact on the user acceptance of such applications. To address this issue, we propose the concept of stateless gateways to augment cloud-based mobile social applications. A stateless gateway is chosen by the cloud to distribute information to nearby interested parties, without requiring any additional state information on the gateway itself. We integrate the concept into a location-based publish/subscribe system and show the resulting performance and cost characteristics through extensive evaluations. Our results show that the stateless concept enables frequent gateway switches, lowering the load on the cellular network by 70% for the scenario of a mobile augmented reality game. At the same time, our system achieves better fairness characteristics among participants due to a more efficient utilization of gateway nodes compared to a less flexible assignment of gateways.

Switching Push and Pull: An Energy Efficient Notification Approach

An increasing number of modern smartphone applications are dependent on information updates from the cloud. To realize such information updates mainly two communication approaches are common, namely push- and pull. Due to different communication patterns both approaches differ in their energy consumption and notification latency. The energy constrained nature of mobile devices entails a sensible selection of the appropriate notification approach. In this paper we provide an evaluation of the energy consumption of both communication approaches. Based on this we provide a transition approach that is able to use the best of both, low latency and low energy consumption. Our results show that energy savings of up to 7% of the total smartphone battery per day can be achieved by switching between both approaches, depending on the context.

A Framework for Publish/Subscribe Protocol Transitions in Mobile Crowds

The increasing number of sensor-equipped mobile devices enables new applications for communication within crowds of people. Ranging from monitoring services that provide insights into the crowds behavior to fully fledged messaging applications for end users, all such applications require communication protocols that are tailored to the characteristics of a mobile ad hoc network MANET. A common communication scheme for such dynamic networks is the publish/subscribe pub/sub paradigm, that offers temporal and spatial decoupling. However, pub/sub protocols for MANETs are designed and evaluated under very restricted conditions regarding the expected mobility, number of users, application workload, and application requirements, targeting rather specific scenarios. In reality, such conditions are subject to change, especially considering peoples behavior during crowded events. In this work, we propose a framework that enables dynamic transitions between different pub/sub protocols based on the currently monitored conditions or caused by an external trigger. We analyze the behavior during transitions and the overhead introduced by our framework through extensive simulations. By using simple pub/sub protocols and switching between them based on the observed conditions, we are able to maintain good service quality at reasonable overhead, thereby enabling applications to operate in dynamic conditions representative of mobile crowds.

DistTM: Collaborative traffic matrix estimation in distributed SDN control planes

Recently, several works propose monitoring approaches for the emerged paradigm of Software-defined Networking. These provide a couple of ideas to retrieve various information about the network state leveraging new concepts for monitoring data collection at flow-level. As existing approaches reduce their scope to networks with a single controller, even sophisticated approaches ignore a potentially great efficiency gap, due to redundant flow measurements by multiple controllers in adjacent networks. To show a possibility how to close this efficiency gap, we propose a solution for collaborative traffic matrix estimation, termed DistTM. It exploits the property that flows traverse multiple networks and are monitored by several controllers. Through collaboration, the resulting monitoring tasks are coordinated and distributed among participating controllers to capture relevant information about all traversing flows, omitting redundant data collection. Conducted simulations reveal that DistTM operates efficiently: the monitoring traffic is significantly reduced, while the traffic matrix entry staleness is slightly affected. Furthermore, DistTM provides different schemes for a fair load balancing on controllers and switches while taking different influencing aspects into consideration.

A step towards a protocol-independent measurement framework for dynamic networks

Existing measurement frameworks typically assume that the communication protocols and mechanisms running on the devices do not change during network operation. However, recent research efforts show that by enabling devices to switch between protocols and mechanisms at runtime the overall network performance can be improved. In this paper, a novel measurement framework that enables the continuous and consistent measurement of monitoring metrics even across such adaptations in networks is presented. The framework exploits monitoring metrics locally on the devices (i) irrespectively of the used mechanisms or protocols on the devices and (ii) allows other mechanisms and applications in the network to adapt to changes by referring monitoring information from the framework. A proof-of-concept prototype of the measurement framework is used to show that the work represents a promising step towards protocol-independent, adaptive monitoring in dynamic networks.

Push vs. Pull: An Energy Perspective (Short Paper)

In many application scenarios, such as traffic guidance or ambient living, services need to notify mobile applications about status changes. Such notifications to mobile devices can be realized using two principal approaches, namely push- and pull-based. Apart from functional differences, the two options likely result in different energy consumption, which is an important aspect due to the battery constraints of contemporary mobile devices. This paper provides a detailed assessment of energy consumption in pull- and push-based notification scenarios, considering different payload sizes and notification intervals. Our results indicate that an educated choice among both options may, depending on the specific application scenario, facilitate energy savings of up to 19%.

Limiting the Footprint of Monitoring in Dynamic Scenarios through Multi-Dimensional Offloading

Multiple offloading techniques are used in todays communication systems. Most approaches rely on cellular offloading to reduce the burden on the cellular infrastructure, especially in crowded situations. While the load on the cellular infrastructure decreases, network participants that are actively involved in the networking effort by device-to-device communication carry the load of a majority of devices. Though, by focusing on the cellular medium for offloading, the increased number of public available network access points remains mostly unused by most approaches. Incorporating access points for offloading entails numerous advantages, such as a reduced load on the cellular data plan of mobile users. In this work, the potentials of multi-dimensional offloading are assessed using the example of a state-of-the-art adaptive monitoring system that, so far, only employs cellular and device-to-device offloading. We show that the system can benefit from adding additional components and protocols that enable multi-dimensional offloading. Through an extensive simulation study we show that combining different offloading techniques leads to significant improvements regarding the achieved service quality (up to 15-fold) and the responsiveness (up to 5-fold), while reducing the load on the mobile nodes by at least 35% even in scenarios with good cellular connectivity.