Drone operations are gaining high interest in many sectors. Continuous and reliable communication between drones and their Ground Control Station (GSC) is crucial for successful and safe drone operations. However, due to the wireless nature of this communication, the Quality of Service (QoS) is often unreliable. Obstacles or cyberattacks (e.g., jamming) can impair communication, endangering drones, operators, and even public safety. In this paper, we therefore analyze drone communication QoS and propose a formal QoS definition to estimate QoS for a given situation and communication interface. We further present an Adaptive Drone Communication Redundancy (ADCR) mechanism to improve drone communication QoS efficiently. Using the estimated and monitored QoS, ADCR dynamically increases the number of used heterogeneous interfaces to communicate redundantly when the QoS is below a certain threshold. To conserve resources, when the QoS threshold is met, the redundancy is reduced again. We evaluate our work using a physical drone testbed which demonstrates that ADCR improves reliability even in the presence of jamming attacks, while creating a 50% lower overhead than fully redundant communication, thus balancing the trade-off between efficiency and redundancy.

Industrial cyber-physical systems require dependable network communication with formal end-to-end reliability guarantees. Striving towards this goal, recent efforts aim to advance the integration of 5 G into Time-Sensitive Networking (TSN). However, we show that IEEE 802.1Qbv TSN schedulers that are unattuned to 5 G packet delay variations may jeopardize any reliability guarantees provided by the 5 G system. We demonstrate this on a case where a 99.99 % reliability in the inner 5G network diminishes to below 10 % when looking at end-to-end communication in TSN. In this paper, we overcome this shortcoming by introducing Full Interleaving Packet Scheduling (FIPS) as a wireless-friendly IEEE 802.1Qbv scheduler. To the best of our knowledge, FIPS is the first to provide formal end-to-end QoS guarantees in wireless TSN. FIPS allows a controlled batching of TSN streams, which improves schedulability in terms of the number of wireless TSN streams by a factor of up to$\times 45$. Even in failure cases, FIPS isolates the otherwise cascading QoS violations to the affected streams and protects all other streams. With formal end-to-end reliability, improved schedulability, and fault isolation, FIPS makes a substantial advance towards dependability in wireless TSN.

Deterministic real-time communication with bounded delay is an essential requirement for many safety-critical cyber–physical systems, and has received much attention from major standardization bodies such as IEEE and IETF. In particular, Ethernet technology has been extended by time-triggered scheduling mechanisms in standards like TTEthernet and Time-Sensitive Networking. Although the scheduling mechanisms have become part of standards, the traffic planning algorithms to create time-triggered schedules are still an open and challenging research question due to the high complexity of the problem. In particular, so-called plug-and-produce scenarios require the ability to extend schedules on the fly within seconds. The need for scalable scheduling and routing algorithms is further supported by large-scale distributed real-time systems like smart energy grids with tight communication requirements. In this paper, we tackle this challenge by proposing two novel algorithms called Hierarchical Heuristic Scheduling (H2S) and Cost-Effective Lazy Forwarding Scheduling (CELF) to create time-triggered schedules for TTEthernet. H2S and CELF are highly efficient and scalable, computing schedules for more than 45,000 streams on random networks with 1000 bridges as well as a realistic energy grid network within seconds or even sub-seconds.

Many applications of cyber-physical systems require real-time communication: manufacturing, automotive, etc. Recent Ethernet standards for Time Sensitive Networking (TSN) offer time-triggered scheduling in order to guarantee low latency and jitter bounds. This requires precise frame transmission planning, which becomes especially hard when dealing with many streams, large networks, and dynamically changing communications. A very promising approach uses conflict graphs, modeling conflicting transmission configurations. Since the creation of conflict graphs is the bottleneck in these approaches, we provide an improvement to the conflict graph creation. We present a randomized selection process that reduces the overall size of the graph in half and three heuristics to improve the scheduling success. In our evaluations we show substantial improvements in the graph creation speed and the scheduling success compared to existing work, updating existing schedules in fractions of a second. Additionally, offline planning of 9000 streams was performed successfully within minutes.

Free WiFi services offer Internet access at many public places like airports or in public transport vehicles. However, the experienced Quality of Service is often poor and unequal between users. While some users can run bandwidth-intensive applications such as video streaming in these networks, others cannot even perform simple web browsing. The reason for this are extensive delays, caused by network congestion of bandwidth-intensive applications, which especially impair interactive applications such as web browsing.In this paper, we propose a novel approach to improve fairness and user experience when sharing common network resources. To this end, we present a Usage-Dependent Quality of Service model (UD-QoS) that dynamically prioritizes network traffic based on the usage intensity of each participant. It shields participants with low usage intensity from congestion delays caused by participants who use the service extensively. We describe the versatile configuration possibilities of UD-QoS and present a Linux-based proof-of-concept implementation.Our evaluations with a physical testbed and popular real-world applications such as video streaming, social media and web browsing show a significant reduction of response times by up to 79% with UD-QoS while keeping processing overhead low. The benefits are particularly large for participants with low usage intensity.

Since network delays can severely impact Networked Control Systems (NCS), both guaranteed Quality of Service (QoS) at the network level and guaranteed stability at the application level in the presence of delays are essential. The recently developed Dynamic Priority Token Bucket (DPTB) aims to meet network-level requirements through dynamic yet deterministic latency bounds that depend on the application’s sending behavior.This concept provides great potential for a combined design method with NCS controllers, which we propose in this paper. We design and implement two approaches that combine DPTB with (1) the well-known robust input/output (DPTB-RobustIO) controller to provide provable stability and (2) a novel multi-level linear quadratic regulator (DPTB-MLQR) to improve control performance.For the evaluation of the approaches, an Ethernet-based NCS with a Linux software switch and an inverted pendulum is used. This benchmark setup for fully automated evaluations of co-designs that combine network scheduling and QoS mechanisms with NCS controllers running on real hardware components is made available as an open source implementation. DPTB-RobustIO and DPTB-MLQR reduced the data rate by up to 26% and increased the control performance by 27% compared to regular token buckets with RobustIO control.

Executing complex simulations on mobile devices such as augmented reality (AR) glasses or smartphones enables many novel pervasive applications. For instance, a physiotherapist can display muscles and bones in real-time as a visual overlay on the patient's body. The major challenge of such pervasive simulations is the complexity of the simulation, which typically exceeds the resources of the mobile device by far. Offloading computationally intensive simulations to a remote server is a promising method to enable real-time simulations on resource-constrained mobile devices without compromising the quality of the simulation results. However, the results of offloaded computations may arrive with an inevitable communication delay, which is critical for real-time simulations and also induces communication overhead. In this work, we tackle these challenges by proposing a novel approach for pervasive simulations on mobile devices. We combine a low-quality local Neural Network (NN) model on the mobile device with a high-quality NN model on a remote server, particularly taking care to integrate delayed updates from the server with the local simulation results. This distributed approach has several advantages over purely local or remote execution models: We benefit from high-quality remote results, while being robust to dynamic delays, server and network failures, and we reduce the communication overhead.

Real-time simulation in augmented reality environments is an important area of research. The simulation model used in this paper simulates the musculoskeletal system, which has many potential applications in physiotherapy, medical education, and rehabilitation. To enable such real-time simulations in augmented reality, high-performance computing clusters are typically required, which can be costly and infeasible in terms of high network delay. This paper proposes SimEdge, a domain-specific edge computing system that enables real-time pervasive simulation in augmented reality environments on heterogeneous providers. This is done by smart offloading decisions based on a continuously updated list of resource providers. SimEdge builds on previous work using surrogate models and leverages scheduling improvements and context-aware data and task placement. Significant improvements in frame rate and input lag are achieved, as well as a reduction in energy consumption. The experimental results show that the proposed approach leads to an 8.3-fold increase in frame rate and a 65.14% reduction in input lag, as well as a 35.07% reduction in energy consumption compared to the local baseline system. These results demonstrate the effectiveness of the approach in improving efficiency and responsiveness.

Many time-sensitive networked systems, such as networked control systems or other cyber/physical systems, require well-defined Quality of Service (QoS) with guaranteed deterministic bounds on network delay. Existing QoS models typically provide no guarantees for excess traffic beyond the traffic specified during the initial admission process. This can lead to a waste of resources when applications overcompensate during resource reservation to avoid traffic violations. In this work, we propose the Dynamic Priority Token Bucket (DPTB), a fundamentally different new QoS model. DPTB permits short-time violations without immediately dropping to best-effort guarantees for excess traffic. Instead, the priority of the application gets degraded to weaker but still deterministic guarantees. At any point in time, the application can calculate the currently guaranteed delay bounds, which depend only on its own past sending behavior, to enable application-level adaptation of the sending rate and application-side prediction of the implications onto the application performance. We designed DPTB as a token bucket extension that can be used on top of several existing scheduling mechanisms, such as the Asynchronous Traffic Shaper of IEEE Time-Sensitive Networking (TSN). Our evaluations show that DPTB is more resilient to bursty cross-traffic, resulting in significantly lower average delays than regular reservations.

Numerical simulations on mobile devices are an important tool for engineers and decision makers in the field. However, providing simulation results on mobile devices is challenging due to the complexity of the simulation, requiring remote server resources and distributed mobile computation. The additional large size of multi-dimensional simulation results leads to the insufficient performance of existing approaches, especially when the bandwidth of wireless communication is scarce. In this article, we present an optimized novel approach utilizing surrogate models and data assimilation techniques to reduce the communication overhead. Evaluations show that our approach is up to 6.5 times faster than streaming results from the server while still meeting required quality constraints.

Simulations are an important part of analyzing and understanding systems, including not only technical but also bio-mechanical subjects such as the musculoskeletal apparatus of the human body. Detailed, biophysical simulations are complex and require a substantial amount of computational resources. With the advent of mobile AR devices such as the Microsoft HoloLens, new challenges arise to run or represent the results of such complex simulations on resource-constrained devices. In this paper we propose a deep-learning-based mobile simulation approach for the contraction of a human muscle model on an AR device (MS HoloLens 2). To elaborate, we present a two-step workflow consisting of simulating the deformation of the 3D geometry of the biceps, of which a subset of points can be interpolated back to full resolution. This allows to either offload the full simulation, just communicating the subset of nodal points, or to use a lower-quality local simulation restricted to the subset. Interpolation is done locally in both cases. The interpolation model consists of a dense, single hidden layer neural network. A mesh simplification method is combined with a genetic algorithm to determine the optimal subset of mesh nodes to interpolate from. In purely local execution, our simulation and interpolation model is able to accurately predict the position of 2809 nodal points based on as few as 30, while using 97.78 % less energy and evaluating up to 1.23 times faster compared to the local reference model. In an ideal distributed scenario energy consumption decreases by 99 % and evaluation time is up to 32.42 times faster. For the latter, it also reduces communication-data to 1.2 % of the full resolution mesh.

Many networked applications, e.g., in the domain of cyber-physical systems, require strict service guarantees for time-triggered traffic flows, usually in the form of jitter and latency bounds. It is a notoriously hard problem to compute a network-wide traffic plan, i.e., a set of routes and transmission schedules, that satisfies these requirements, and dynamic changes in the flow set add even more challenges. Existing traffic-planning methods are ill-suited for dynamic scenarios because they either suffer from high computational cost, can result in low network utilization, or provide no explicit guarantees when transitioning to a new traffic plan that incorporates new flows. Therefore, we present a novel approach for dynamic traffic planning of time-triggered flows. Our conflict-graph-based modeling of the traffic planning problem allows for the reconfiguration of active flows to increase the network utilization, while also providing per-flow QoS guarantees during the transition to the new traffic plan. Additionally, we introduce a novel heuristic for computing the new traffic plans. Evaluations of our prototypical implementation show that we can efficiently compute new traffic plans in scenarios with hundreds of active flows for a wide range of settings.

The increasing number of cloud offerings makes it more challenging to find services that realize an optimal architecture. Hence, modeling cloud applications with the help of platform-independent models as known from Model-Driven Architecture (MDA) should aid developers in designing best-practice architectures. However, refining platform-independent architecture models into an architecture with concrete services might lead to a large number of potential solutions, raising the question of which solution is the best. Therefore, we propose a framework that uses meta-heuristics to approximate the search of concrete solutions for component-based architectures, using the notion of refinement trees to encode the potential solution space of abstract components. In this paper, we show how to transform the solution space of the refinement trees into a suitable input for the meta-heuristic. Moreover, we provide a class of loss functions with the objective to minimize cost, while also considering quality of service (QoS) constraints to demonstrate possible applications of the framework. The evaluation uses the Harmony Search algorithm as a concrete implementation of a meta-heuristic to exemplify our framework. We analyzed different cloud architecture examples from Microsoft Azure, where we show the advantages of the heuristic approach by proposing cost-minimal services for a given QoS constraint.

Recently, named data networking (NDN) has been introduced to connect the world of computing devices via naming data instead of their containers. Through this strategic change, NDN brings several new features to network communication, including in-network caching, multipath forwarding, built-in multicast, and data security. Despite these unique features of NDN networking, there exist plenty of opportunities for continuing developments, especially with packet forwarding and caching. In this context, we introduce liteNDN, a novel forwarding and caching strategy for NDN networks. liteNDN comprises a cooperative forwarding strategy through which NDN routers share their knowledge, i.e. data names and interfaces, to optimize their packet forwarding decisions. Subsequently, liteNDN leverages that knowledge to estimate the probability of each downstream path to swiftly retrieve the requested data. Additionally, liteNDN exploits heuristics, such as routing costs and data significance, to make proper decisions about caching normal as well as segmented packets. The proposed approach has been extensively evaluated in terms of the data retrieval latency, network utilization, and the cache hit rate. The results showed that liteNDN, compared to conventional NDN forwarding and caching strategies, achieves much less latency while reducing the unnecessary traffic and caching activities.

Traffic planning is the key enabler of time-triggered real-time communication in distributed systems, and it is known to be notoriously hard. Current approaches predominantly tackle the problem in the domain of the traffic planning problem, e.g., by formulating constraints on the transmission schedules for individual data streams, or the links used by the data streams. This results in a high degree of coupling of the configuration of an individual data stream and the global (network-wide) traffic configuration with detrimental effects on the scalability and runtime of the planning phase.In contrast, we present a configuration-conflict graph based approach, which solves the original traffic planning problem by searching an independent vertex set in the conflict graph. We show how to derive the configuration-conflict graph, and discuss the conceptual advantages of this approach. To show the practical advantages of the conflict-graph based traffic planning approach we additionally present a proof-of-concept implementation and evaluate it against a reference ILP-based implementation. In our evaluations, our proof-of-concept implementation of the conflict-graph based approach outperforms the reference ILP and is more memory efficient, making it a promising alternative to current constraint-based traffic planning approaches.

Industry 4.0 and the vision of smart factories drive the need for real-time communication. Time-Sensitive Networking (TSN) augments the IEEE Std 802.1Q with a family of mechanisms enabling real-time communication. One of the key mechanisms is the Time-Aware Shaper (TAS) implementing a TDMA scheme on a traffic class basis. With proper synchronization it can even be used to schedule individual frames or streams. With this capability, the network can guarantee communication deadlines, bounded latency, and bounded jitter. However, for these guarantees a system-wide schedule needs to be calculated, which is an NP-hard problem. Current approaches are mainly based on constraint programming and optimization problems, and, therefore do not scale well for larger topologies and number of streams. In this paper, our contribution is twofold: first, we propose a scheduling model for converged networks supporting different traffic types and, secondly, we introduce a novel procedure for schedule planning of isochronous traffic which exploits the hierarchical structure of factory networks. To this end, we split the network into sub-networks and use a two-stage approach based on a heuristic and tracing. Our evaluation shows that the new scheduling approach outperforms the reference scheduler by more than two orders of magnitude with regard to execution time.

Recently, indoor modeling has gained increased attention, thanks to the immense need for realizing efficient indoor location-based services. Indoor environments differ from outdoor spaces in two aspects: spaces are smaller and there are many structural objects such as walls, doors, and furniture. To model the indoor environments in a proper manner, novel data acquisition concepts and data modeling algorithms have been devised to meet the requirements of indoor spatial applications. In this realm, several research efforts have been exerted. Nevertheless, these efforts mostly suffer either from adopting impractical data acquisition methods or from being limited to 2D modeling. To overcome these limitations, we introduce the MapSense approach, which automatically derives indoor models from 3D point clouds collected by individuals using mobile devices, such as Google Tango, Apple ARKit, and Microsoft HoloLens. To this end, MapSense leverages several computer vision and machine learning algorithms for precisely inferring the structural objects. In MapSense, we mainly focus on improving the modeling accuracy through adopting formal grammars that encode design-time knowledge, i.e., structural information about the building. In addition to modeling accuracy, MapSense considers the energy overhead on the mobile devices via developing a probabilistic quality model through which the mobile devices solely upload high-quality point clouds to the crowd-sensing servers. To demonstrate the performance of MapSense, we implemented a crowd-sensing Android App to collect 3D point clouds from two different buildings by six volunteers. The results showed that MapSense can accurately infer the various structural objects while drastically reducing the energy overhead on the mobile devices.

Typically, Function-as-a-Service (FaaS) involves state-less replication with very large numbers of instances. The reliability of such services can be evaluated using Bayesian Networks and k-out-of-n models. However, existing k-out-of-n models do not scale to the larger number of hosts of FaaS services. Therefore, we propose a scalable k-out-of-n model in this paper with the same semantics as the standard k-out-of-n voting gates in fault trees, enabling the reliability analysis of FaaS services.

We present a communication abstraction for Networked Control Systems that is characterized by a slotted transmission classification model. We discuss, how such a model can be implemented over local area networks by using IEEE Time Sensitive Networking methods. Furthermore, it is shown how asymptotic stability can be analyzed for linear systems that communicate over such a network. Based on the stability result, a controller design procedure is derived that takes the information captured in the network model into account. Further topics and related open problems that are implicated by the proposed model are briefly discussed as an outlook.

Internet of Things (IoT) is expanding at a rapid rate where it allows for virtually endless opportunities and connections to take place. In general, IoT opens the door to a myriad of applications but also to many challenges. One of the major challenges is how to efficiently retrieve the sensory data from "resources-limited" IoT devices. Such devices typically have a restricted energy budget, which broadly hinders their direct connection to the Internet. In this realm, modern mobile devices, e.g. smartphones, tablets, smartwatches, have been harnessed to bridge between the low-power IoT devices and the Internet. However, the current vision which mainly relies on designing siloed gateways, i.e. a separate gateway/App for each IoT device, is certainly impractical, especially with the rapid growth in the number of IoT devices. Furthermore, the energy efficiency of the smart mobile devices hosting the IoT gateways has to be thoroughly considered. To tackle these challenges, we introduce GaaS (Gateway as a Service), a cross-platform gateway architecture for opportunistically retrieving sensory data from the low-power IoT sensors. Through Bluetooth low energy radios, GaaS is capable of simultaneously connecting to several nearby IoT sensors. To this end, we devise two distinct priority-based scheduling algorithms, namely the EP-WSM and FEP-AHP schedulers, which rank the detected IoT sensors, before estimating the connection time for each IoT sensor. The intuition behind ranking the IoT sensors is to improve the data retrieval rate from these sensors together with reducing the energy overhead on the mobile devices. Additionally, GaaS encompasses a self-adaptive engine to automatically balance the trade-off between energy efficiency and data retrieval rate through switching between schedulers according to the runtime dynamics. To demonstrate the effectiveness of GaaS, we implemented an IoT testbed to evaluate the energy consumption, the latency, and the data retrieval rate. The results show that using GaaS, compared to siloed gateways, we can identify up to 18% savings in the consumed energy while requiring much less data retrieval time.

Recently, mobile crowdsensing has become an appealing paradigm thanks to the ubiquitous presence of powerful mobile devices. Indoor mapping, as an example of crowdsensingdriven applications, is essential to provide many indoor locationbased services, such as emergency response, security, and tracking/navigation in large buildings. In this realm, 3D point clouds stand as an optimal data type which can be crowdsensed-using currently-available mobile devices, e.g. Google Tango, Microsoft Hololens and Apple ARKit-to generate floor plans with different levels of detail, i.e. 2D and 3D mapping. However, collecting such bulky data from "resources-limited" mobile devices can significantly harm their energy efficiency. To overcome this challenge, we introduce GreenMap, an energy-aware architectural framework for automatically mapping the interior spaces using crowdsensed point clouds with the support of structural information encoded in formal grammars. GreenMap reduces the energy overhead through projecting the point clouds to several filtration steps on the mobile devices. In this context, GreenMap leverages the potential of approximate computing to reduce the computational cost of data filtering while maintaining a satisfactory level of modeding accuracy. To this end, we propose two approximation strategies, namely DyPR and SuFFUSION. To demonstrate the effectiveness of GreenMap, we implemented a crowdsensing Android App to collect 3D point clouds from two different buildings. We show that GreenMap achieves significant energy savings of up to 67.8%, compared to the baseline methods, while generating comparable floor plans.

Location information sharing on popular online social networking platforms like Facebook and Foursquare brings mutual benefits for the users of these platforms (e.g., free locationbased services) as well as the platform providers (e.g., locationbased businesses). An obvious problem however that impedes these mutual benefits are privacy concerns related to location data of users, which also curb their active participation. In this paper, we analyze the role of existing location privacypreserving mechanisms in minimizing this mutual loss of benefits. Our analysis reveals that most existing mechanisms either ignore social platform related user-privacy concerns or they disregard location data-quality related demands of the platform providers. Moreover, we also point out concrete research gaps and implementation issues related to existing privacy mechanisms.

IEEE 802.1Q networks with extensions for time-sensitive networking aim to enable converged networks. Converged networks support hard-real time communication services in addition to the currently supported services classes. Real-time communication in these networks requires routes and schedules for the real-time transmissions. We present a formulation in the integer linear programming (ILP) framework which models the joint routing and scheduling problem for flows of periodic real-time transmissions in converged TSN networks. In the joint routing and scheduling problem, both routes and schedules for real-time transmissions are computed in one step, i.e. we do not schedule over predefined routes. We explore the practical limitations of this approach by evaluating the runtime of problem instances with widely varying parameters with a state-of-the-art ILP solver. The observed solver runtimes indicate the qualitative impact of the number of real-time flows, the size of the network, the transmission frequency of real-time transmissions, and the network topology.

Several networking architectures have been developed atop IEEE 802.3 networks to provide real-time communication guarantees for time-sensitive applications in industrial automation systems. The basic principle underlying these technologies is the precise transmission scheduling of time-triggered traffic through the network for providing deterministic and bounded latency and jitter. These transmission schedules are typically synthesized offline (computational time in the order of hours) and remain fixed thereafter, making it difficult to dynamically add or remove network applications. This paper presents algorithms for incrementally adding time-triggered flows in a time-sensitive software-defined network (TSSDN). The TSSDN is a network architecture based on software-defined networking, which provides real-time guarantees for time-triggered flows by scheduling their transmissions on the hosts (network edge) only. These algorithms exploit the global view of the control plane on the data plane to schedule and route time-triggered flows needed for the dynamic applications in the Industrial Internet of Things (Industry 4.0). The evaluations show that these algorithms can compute incremental schedules for time-triggered flows in subseconds with an average relative optimality of 68%.

Recent years have seen an evolution of software-defined networking (SDN) control plane architectures, starting from simple monolithic controllers, over modular monolithic controllers, to distributed controllers. We observe, however, that today's distributed controllers still exhibit inflexibility with respect to the distribution of control logic. Therefore, we propose a novel architecture of a distributed SDN controller, providing maximum flexibility with respect to distribution and improved manageability. Our architecture splits control logic into lightweight control modules, called controllets, based on a micro-kernel approach, reducing common controllet functionality to a bare minimum and factoring out all higher-level functionality. Lightweight controllets also allow for pushing control logic onto switches and enable local processing of data plane events to minimize control latency and communication overhead while leveraging SDN's global view to maximize control decision quality. Controllets are interconnected through a message bus supporting the publish/subscribe communication paradigm with specific extensions for content-based message filtering. Publish/subscribe allows for complete decoupling of controllets to further facilitate control plane distribution. Furthermore, we identify crucial requirements for practical on-switch deployments, where we employ lightweight virtualization techniques to ensure a safe control plane operation. We evaluate both, the scalability and performance properties of our architecture, including its deployment on a white-box networking hardware switch.

Recent years have seen an evolution of SDN control plane architectures, starting from simple monolithic controllers, over modular monolithic controllers, to distributed controllers. We observe, however, that today's distributed controllers still exhibit inflexibility with respect to the distribution of control logic. Therefore, we propose a novel architecture of a distributed SDN controller in this paper, providing maximum flexibility with respect to distribution. Our architecture splits control logic into light-weight control modules, called controllets, based on a micro-kernel approach, reducing common controllet functionality to a bare minimum and factoring out all higher-level functionality. Light-weight controllets also allow for pushing control logic onto switches and enable local processing of data plane events to minimize latency and communication overhead. Controllets are interconnected through a message bus supporting the publish/subscribe communication paradigm with specific extensions for content-based OpenFlow message filtering. Publish/subscribe allows for complete decoupling of controllets to further facilitate control plane distribution. We evaluate both, the scalability and performance properties of our architecture, including its deployment on a White Box networking hardware switch.

Recent developments in networking hardware and software-defined networking have enabled full distribution of network control to reduce control latency and increase reliability. However, both, hardware and software of current white-box networking hardware are highly heterogeneous, which limits the deployment and operation of switch-local control applications. Furthermore, switch-local control raises yet unconsidered security concerns. In this paper, we present our concept of in-forward-element processing, which leverages the open access to the control plane of white-box networking hardware to deploy control logic directly onto switches. We combine local control applications with lightweight virtualization to cope with networking hardware heterogeneity and to achieve required isolation properties and ease of management. Beyond distributed network control, we show this scheme is also beneficial for implementing switch-local virtual network functions (NFV), processing packets. Highlighting the practicability of the concepts, we provide an overview of the current white-box networking hardware and software landscape and their compatibility with lightweight virtualization technologies. To this end, we perform an empirical evaluation of NOS-virtualization combinations on such hardware and compare the results with respect to incurring virtualization overhead.

Recently, crowd-sensing has rapidly been evolved thanks to the technological advancement in personal mobile devices. This emerging technology opens the door for numerous applications to collect sensory data from the crowd. To provide people with a motive for participating in data acquisition, the crowd-sensing systems have to sidestep burdening the resources allocated to the mobile devices, i.e. computing power and energy budget. In this paper, we propose iSense, a novel framework for reducing the energy costs of participating in crowd-sensing. We mainly target the superfluous energy overhead on the mobile devices to sense and report their position information to the back-end servers. To relieve such an overhead, iSense entirely offloads the localization burden to the crowd-sensing servers. In this manner, iSense enables the utilization of advanced localization approaches thanks to the high resources of the crowd-sensing servers. To this end, iSense opportunistically exploits the “already-existent” network signaling exchanged frequently between the mobile devices and the WiFi networks or the cellular networks. To collect the localization data, we implement a lightweight data collection algorithm on a set of off-the-shelves access points. As a case study, we implement a two-step localization method, including a coarse- and a fine-grained localization. In this regard, compressed sensing is employed to estimate the fine-grained solution. To assess the effectiveness of iSense, we implemented a testbed to evaluate the energy consumption and the localization accuracy with different mobility and usage patterns. The results show that using iSense, compared to some baseline methods, we can identify up to 95% savings in the consumed energy.

Recently, several approaches have been proposed to automatically model indoor environments. Most of such efforts principally rely on the crowd to sense data such as motion traces, images, and WiFi footprints. However, large datasets are usually required to derive precise indoor models which can negatively affect the energy efficiency of the mobile devices participating in the crowd-sensing system. Furthermore, the aforementioned data types are hardly suitable for deriving 3D indoor models. To overcome these challenges, we propose GraMap, a QoS-aware automatic indoor modeling approach through crowd-sensing 3D point clouds. GraMap exploits a recently-developed sensors fusion mechanism, namely Tango technology, to cooperatively collect point clouds from the crowd. Afterward, a set of backend servers extracts the required geometrical information to derive indoor models.

In today's online social networks such as Facebook, users increasingly share their location information as a popular type of personal information. However, since location data can leak privacy-sensitive information about individuals such as the type of places they like to visit, a number of location obfuscation mechanisms have been proposed to avoid such disclosure. These mechanisms publish bigger regions containing the actual user location in order to make it imprecise. Thus an attacker may find it hard to precisely locate the user in a privacy-sensitive place such as a hospital.

Currently, various hardware and software companies are developing augmented reality devices, most prominently Microsoft with its Hololens. Besides gaming, such devices can be used for serious pervasive applications, like interactive mobile simulations to support engineers in the field. Interactive simulations have high demands on resources, which the mobile device alone is unable to satisfy. Therefore, we propose a framework to support mobile simulations by distributing the computation between mobile device and a remote server. For the computation of parameter-dependent solutions of the simulation, we use the reduced basis method, which allows to drastically reduce the computation time and energy consumption. We present three approaches for the distributed execution of the reduced basis method between mobile device and server. Evaluations show that we can speed-up the numerical computation to over 131 times while using 73 times less energy compared to offloading everything to a server.

With the increasing popularity of software-defined networking (SDN), ternary content-addressable memory of switches can be directly accessed by a publish/subscribe middleware to perform filtering operations at low latency. In this way, three important requirements for a publish/subscribe middleware can be fulfilled, namely, bandwidth efficiency, line-rate performance, and low latency in forwarding messages between producers and consumers. Nevertheless, it is challenging to sustain line-rate performance in the presence of dynamically changing interests of producers and consumers. In this paper, we realize a scalable, SDN-based publish/subscribe middleware, called PLEROMA, that performs efficient forwarding at line-rate. Moreover, PLEROMA offers methods to efficiently reconfigure a deployed topology in the presence of dynamic subscriptions and advertisements. We evaluate the performance of both the data plane and the control plane of PLEROMA to support our claim. Furthermore, we evaluate and benchmark the performances of SDN-compliant hardware and software switches in the context of our middleware.

With the fast adoption of location-enabled devices, Location-based Applications (LBAs) have become widely popular. While LBAs enable highly useful concepts such as geo-social networking, their use also raises serious privacy concerns as it involves sharing of location data with non-trusted third parties. In this respect, we propose an approach that protects the frequently visited locations of users, e.g., a bar, against inferences from long-term monitoring of their location data. Such inferences equate a privacy leak as they reveal a user's personal behavior and interests to possibly malicious non-trusted parties. To this end, we first present a study of a dataset of location check-ins to show the existence of this threat among users of LBAs. We then propose our approach to protect visit-frequency of the users to different locations by distributing their location data among multiple third-party Location Servers. This distribution not only serves to avoid a single point of failure for privacy in our system, it also allows the users to control which LBA accesses what information about them. We also describe a number of possible attacks against our privacy approach and evaluate them on real-data from the check-ins dataset. Our results show that our approach can effectively hide the frequent locations while supporting good quality-of-service for the LBAs.

Code offloading strives for increasing the energy efficiency and execution speed of mobile applications on resource-constrained mobile devices. First approaches considered only a code offloading between two (or three) tiers, executing code either locally on the mobile device or remotely on a powerful server in the vicinity or in a distant cloud. However, new execution environments comprise multiple tiers, containing highly distributed heterogeneous resources.

Updating a network is an essential and continual task in the management of today's softwarized networks. When applying updates on distributed network elements, desired network properties, such as drop- and loop-freeness, might be transiently violated. Although being crucial, update consistency has yet been less considered in network management. In this paper, we argue for incorporating the particularities of update consistency into the reconfiguration process of continuous network management. We present a generic management architecture allowing for an appropriate selection of an update mechanism and its parameters based on expected inconsistency effects. We investigate update consistency for the case of multicast routing and show in an extensive analysis why simultaneous drop- and duplicate-freeness is not possible. We present an update procedure for multicast routing updates that identifies critical update steps, which are fed back into the reconfiguration process, along with a lightweight approach that allows for the selection of an update strategy, preventing either drops or duplicates. Furthermore, we present an optimization of an existing powerful, but resource-intensive update approach as well as an approach for in-network filtering of duplicates.

Recently, a new class of mobile applications has appeared that takes into account the behavior of physical phenomenon. Prominent examples of such applications include augmented reality applications visualizing physical processes on a mobile device or mobile cyber-physical systems like autonomous vehicles or robots. Typically, these applications need to solve partial differential equations (PDE) to simulate the behavior of a physical system. There are two basic strategies to numerically solve these PDEs: (1) offload all computations to a remote server, (2) solve the PDE on the resource-constrained mobile device. However, both strategies have severe drawbacks. Offloading will fail if the mobile device is disconnected, and resource constraints require to reduce the quality of the solution. Therefore, we propose a new approach for mobile simulations using a hybrid strategy that is robust to communication failures and can still benefit from powerful server resources. The basic idea of this approach is to dynamically decide on the placement of the PDE solver based on a prediction of the wireless link availability using Markov Chains. Our tests based on measurement in real cellular networks and real mobile devices show that this approach is able to keep deadline constraints in more than 61 % of the cases compared to a pure offloading approach, while saving up to 74 % of energy compared to a simplified approach.

End users execute today on their smart phones different kinds of mobile applications like calendar apps or high-end mobile games, differing in local resource usage. Utilizing local resources of a smart phone heavily, like playing high-end mobile games, drains its limited energy resource in few hours. To prevent the limited energy resource from a quick exhaustion, smart phones benefit from executing resource-intensive application parts on a remote server in the cloud (code offloading). During the remote execution on the remote server, a smart phone waits in idle mode until it receives a result. However, code offloading introduces computation and communication overhead, which decreases the energy efficiency and induces monetary cost. For instance, sending or receiving execution state information to or from a remote server consumes energy. Moreover, executing code on a remote server instance in a commercial cloud causes monetary cost. To keep consumed energy and monetary cost low, we present in this paper the concept of remote-side caching for code offloading, which increases the efficiency of code offloading. The remote-side cache serves as a collective storage of results for already executed application parts on remote servers, avoiding the repeated execution of previously run application parts. The smart phone queries the remote-side cache for corresponding results of resource-intensive application parts. In case of a cache hit, the smart phone gets immediately a result and continues the application execution. Otherwise, it migrates the application part and waits for a result of the remote execution. We show in our evaluation that the use of a remote-side cache decreases energy consumption and monetary cost for mobile applications by up to 97% and 99%, respectively.

Modern mobile devices like smart phones and tablets are equipped with powerful processing and memory resources, enabling resource-intensive mobile applications such as high-end mobile games. The main limitation, however, remains the energy resource. To improve the energy efficiency, code offloading

While location-based services are already well established in outdoor scenarios, they are still not available in indoor environments. The reason for this can be found in two open problems: First, there is still no off-the-shelf indoor positioning system for mobile devices and, second, indoor maps are not publicly available for most buildings. While there is an extensive body of work on the first problem, the efficient creation of indoor maps remains an open challenge. We tackle the indoor mapping challenge in our MapGENIE approach that automatically derives indoor maps from traces collected by pedestrians moving around in a building. Since the trace data is collected in the background from the pedestrians' mobile devices, MapGENIE avoids the labor-intensive task of traditional indoor map creation and increases the efficiency of indoor mapping. To enhance the map building process, MapGENIE leverages exterior information about the building and uses grammars to encode structural information about the building. Hence, in contrast to existing work, our approach works without any user interaction and only needs a small amount of traces to derive the indoor map of a building. To demonstrate the performance of MapGENIE, we implemented our system using Android and a foot-mounted IMU to collect traces from volunteers. We show that using our grammar approach, compared to a purely trace-based approach we can identify up to four times as many rooms in a building while at the same time achieving a consistently lower error in the size of detected rooms.

The relevance of graphical functions in vehicular applications has increased significantly during the few last years. Modern cars are equipped with multiple displays used by different applications such as speedometer or navigation system. However, so far applications are restricted to using dedicated displays. In order to increase flexibility, the requirement of sharing displays between applications has emerged. Sharing displays leads to safety and security concerns since safety-critical applications as the dashboard warning lights share the same displays with uncritical or untrusted applications like the navigation system or third-party applications. To guarantee the safe and secure sharing of displays, we present a formal model for defining and controlling the access to display areas in this paper. We prove the validity of this model, and present a proof-of-concept implementation to demonstrate the feasibility of our concept.

In this paper, we propose a concept for improving the energy efficiency and resource utilization of cloud infrastructures by combining the benefits of heterogeneous machine instances. The basic idea is to integrate low-power system on a chip (SoC) machines and high-power virtual machine instances into so-called Elastic Tandem Machine Instances (ETMI). The low-power machine serves low load and is always running to ensure the availability of the ETMI. When load rises, the ETMI scales up automatically by starting the high-power instance and handing over traffic to it. For the non-disruptive transition from low-power to high-power machines and vice versa, we present a handover mechanism based on software-defined networking technologies. Our evaluations show the applicability of low-power SoC machines to serve low load efficiently as well as the desired scalability properties of ETMIs.

Many location-based applications such as geo-social networks rely on location services storing mobile object positions. To update positions on location servers, position update protocols are used. On the one hand, these protocols decide when an update has to be sent to ensure a certain quality of position information. On the other hand, they try to minimize the energy consumption of the mobile device by reducing communication to a minimum.

The advent of mobile phones paved the way for a new paradigm for gathering sensor data termed Public Sensing (PS). PS uses built-in sensors of mobile devices to opportunistically gather sensor data. For instance, the microphones of a crowd of mobile phones can be used to capture sound samples, which can be used to construct a city noise map. A great challenge of PS is to reduce the energy consumption of mobile devices since otherwise users might not be willing to participate. One crucial part in the overall power consumption is the energy required for the communication between the mobile devices and the infrastructure. In particular, the communication required for sending sensing queries to mobile devices has been largely neglected in the related work so far. Therefore, in this paper, we address the problem of minimizing communication costs for the distribution of sensing queries. While existing systems simply broadcast sensing queries to all devices, we use a selective strategy by addressing only a subset of devices. In order not to negatively affect the quality of sensing w.r.t. completeness, this subset is carefully chosen based on a probabilistic sensing model that defines the probability of mobile devices to successfully perform a given sensing query. Our evaluations show that with our optimized sensing query distribution, the energy consumption can be reduced by more than 70% without significantly reducing the quality of sensing.

The proliferation of modern smartphones has given rise to Public Sensing, a new paradigm for data acquisition systems utilizing smartphones of mobile participants. In this paper, we present DrOPS, a system for improving the efficiency of data acquisition in Public Sensing systems. DrOPS utilizes a model-driven approach, where the number of required readings from mobile smartphones is reduced by inferring readings from the model. Furthermore, the model can be used to infer readings for positions where no sensor is available. The model is directly constructed from the observed phenomenon in an online fashion. Using such models together with a client-specified quality bound, we can significantly reduce the effort for data acquisition while still reporting data of required quality to the client. To this effect, we develop a set of online learning and control algorithms to create and validate the model of the observed phenomenon and present a sensing task execution system utilizing our algorithms in this paper. Our evaluations show that we obtain models in a matter of just hours or even minutes. Using the model-driven approach for optimizing the data acquisition, we can save up to 80% of energy for communication and provide inferred temperature readings for uncovered positions matching an error-bound of 1°C up to 100 % of the time.

Nowadays, millions of users share their complete movement trajectory online when using real-time traffic monitoring applications, pay-as-you-drive insurances, or when sharing their last road trip with friends. However, many users still hesitate to use location-based applications as they are not willing to reveal, for instance, their driving behavior or the occurrence of a speeding violation. Therefore, we present novel speed protection algorithms protecting users from revealing a violation of given speed limits when using location-based applications. Our algorithms support time-based and distance-based position updates. To protect positions indicating a speeding violation, we either adjust temporal information by delaying position updates or adjust their spatial information. We evaluate our algorithms by using real world traces and show that the protected movement trajectory of the user is of high quality even after removing speeding violations.

Utilizing peoples' mobile devices for gathering sensor data has attracted a lot of attention within the last few years. As a result, a great variety of systems for sensing environmental phenomena like temperature or noise have been proposed. However, most of these systems do not take into account that mobile devices have only limited energy resources. For instance, an often assumed prerequisite is that mobile devices are always aware of their position. Given the fact that a position fix is a very energy consuming operation, continuous positioning would quickly drain a device's battery. Since the owners of the mobile devices will not tolerate a significant reduction of the devices' battery lifetime, such an approach is not suitable. To address this issue we present PSense, a flexible system for efficiently gathering sensor data with mobile devices. By avoiding unnecessary position fixes, PSense reduces the energy consumption of mobile devices by up to 70% compared to existing mobile sensing approaches. This is achieved by introducing an adaptive positioning mechanism and by utilizing energy efficient short-range communication to exchange position related information.

Recent forecasts predict that the amount of cellular data traffic will significantly increase within the next few years. The reason for this trend is on the one hand the high growth rate of mobile Internet users and on the other hand the growing popularity of high bandwidth streaming applications. Given the fact that cellular networks (e.g. UMTS) have only limited capacity, the existing network infrastructure will soon reach its limits. As a result, the concept of traffic offloading attracts more and more attention in research since it aims at the reduction of cellular traffic by shifting it to local-area networks like Wifi. One particular form of traffic offloading is known as opportunistic traffic offloading and follows the basic idea to shift traffic from the cellular network to the level of inter-device communication of mobile devices. To perform opportunistic traffic offloading in an efficient way, assumptions about the prospective inter-device connectivity of the mobile devices have to be made. In general, the more inter-device connections are possible the more traffic can be offloaded. To utilize this fact, we developed the TOMP system. TOMP is the first opportunistic traffic offloading system that uses movement predictions of mobile users to analyze the prospective inter-device connectivity. In this paper we propose three different metrics for analyzing movement predictions and present an algorithm, which uses these metrics to utilize an efficient opportunistic traffic offloading. To evaluate TOMP, we show by simulation that we can save up to 40% of cellular messages in comparison to a typical cellular network.

Location-based applications such as Facebook Places, Foursquare, or Loopt attract millions of users by implementing point of interest finders, friend finders, geosocial networking, etc. Typically, these applications act as clients to a location service such as Google Latitude or Yahoo Fire Eagle, which manage mobile object positions and ensure the scalability to provide various clients with mobile object positions. However, exposing precise user positions raises user privacy concerns, especially if location service providers are not fully trusted, and private position information could be “lost”, leaked, stolen, etc. To enable the secure management of private user positions on non-trusted location servers (LSs), we present novel position sharing approaches based on the concept of multi-secret sharing. Our approaches split up a precise user position into position shares, which are distributed to different LSs of different providers such that a compromised provider only reveals user positions with degraded precision. On the other hand, clients can combine several shares queried from different LSs to increase their provided precision without the need to store precise information at a single LS. We propose two position sharing approaches: PShare-SLM is the first position sharing approach presented so far for symbolic location models. For geometric location models, we present PShare-GLM, which improves existing geometric position sharing approaches [1] by considering continuous position updates and by increasing the robustness against various attacks.

The on-line processing of high volume data streams is a prerequisite for many modern applications relying on real-time data such as global sensor networks or multimedia streaming. In order to achieve efficient data processing and scalability w.r.t. the number of distributed data sources and applications, in-network processing of data streams in an overlay network of data processing operators has been proposed. For such stream processing overlay networks, the placement of operators onto physical hosts plays an important role for the resulting quality of service - in particular, the end-to-end latency - and network load. To this end, we present an enhanced placement algorithm that minimizes the network load put onto the system by a stream processing task under user-defined delay constraints in this paper. Our algorithm finds first the optimal solution in terms of network load and then degrades this solution to find a constrained optimum. In order to reduce the overhead of the placement algorithm, we included mechanisms to reduce the search space in terms of hosts that are considered during operator placement. Our evaluations show that this approach leads to an operator placement of high quality solution while inducing communication overhead proportional only to a small percentage of the total hosts.

With the increasing proliferation of small and cheap GPS receivers, a new way of generating road maps could be witnessed over the last few years. Participatory mapping approaches like OpenStreetMap introduced a way to generate road maps collaboratively from scratch. Moreover, automatic mapping algorithms were proposed, which automatically infer road maps from a set of given GPS traces. Nevertheless, one of the main problems of these maps is their unknown quality in terms of accuracy, which makes them unreliable and, therefore, not applicable for the use in critical scenarios. To address this issue, we propose MapCorrect: An automatic map correction and validation system. MapCorrect automatically collects GPS traces from people's mobile devices to correct a given road map and validate it by identifying those parts of the map that are accurately mapped with respect to some user provided quality requirements. Since fixing a GPS position is a battery draining operation, the collection of GPS data raises concerns about the energy consumption of the participating mobile devices. We tackle this issue by introducing an optimized sensing mechanism that gives the mobile devices notifications indicating those parts of the map that are considered as sufficiently mapped and, therefore, require no further GPS data for their validation. Furthermore, we show by simulation that using this approach up to 50% of the mobile phones' energy can be saved while not impairing the effectiveness of the map correction and validation process at all.

Public Sensing is a new paradigm for developing large-scale sensor networks at low cost by utilizing mobile phones that are already surrounding us in our everyday lives. In this paper we present a sensor network abstraction layer for creating flexible public sensing systems that can execute arbitrary queries. To this effect we develop several algorithms to select mobile nodes for executing a query. These algorithms allow a user to define a trade-off between quality and efficiency of query execution by choosing an appropriate algorithm. Our evaluations show that we can achieve a 99% increase in efficiency with the most efficient approaches and only about 10% decrease in result quality under worst conditions.

Many novel location-based services (LBS) such as a friend finder service require knowledge about the positions of mobile users. Usually, location services are used to manage these positions, and for providing basic functionality like spatial range queries or spatial events to the LBS. Managing and using the positions of mobile users raises privacy issues, in particular, if the providers of LBS and location services are only partially trusted. Many different approaches for preserving a user's privacy have been proposed in the literature, e.g. location obfuscation and the k-anonymity concept. However, most of them are not suitable if both LBS and location service providers are non-trusted. In contrast to these approaches, we present a novel approach for the secure management of private position information in partially trusted system environments. The main contribution in this paper is a position sharing concept which allows for the distribution of position information (shares) of strictly limited accuracy onto several location servers of different providers. With this approach, a compromised server will only reveal information of limited accuracy. Moreover, we will show how position shares of coarse granularity from multiple location servers can be fused into information of higher precision to satisfy the accuracy requirements of different LBS.

This paper introduces mechanisms for the automated detection of mobile objects in urban areas. Widely available devices such as mobile phones with integrated proximity sensors such as RFID readers or Bluetooth cooperatively perform sensing operations to discover mobile objects. In this paper, we propose a coverage metric for assessing the completeness of sensing that considers spatial and temporal aspects. To maximize coverage while minimizing energy consumption of mobile nodes, we propose both a centralized and a distributed coordination algorithm for selecting nodes that need to sense. Moreover, we present strategies that allow selected nodes to perform efficient sense operations. By extensive simulations, we show that distributed coordination achieves drastic energy savings of up to 63%, while limiting the coverage loss to 13%. Moreover, we show that the centralized algorithm loses less than 1% coverage compared to the maximum possible coverage.

Context-based communication allows for the dissemination of messages to mobile users with a specified context, i.e. at a location and with certain attribute values. This enables, e.g., a message to students on campus attending a certain class, with information about a study group for an upcoming exam. An overlay network of context-aware routers efficiently disseminate the messages to all matching receivers. Directed forwarding of such messages requires that the routers maintain knowledge about the contexts of connected users. Global knowledge, i.e., each router knowing about every user, scales poorly, though, because of the necessary updates.

Wireless Mesh Networks are cost-efficient medium-scale networks that have the potential to serve as an infrastructure for advanced location-based services. As a basis for these services we present a routing algorithm that allows to address intuitive symbolic coordinates. This algorithm is based on a proactively maintained geographic routing structure that mimics the structure of a symbolic location model. Message forwarding is done greedily along short paths defined by a symbolic location model and if this fails, through an hierarchical overlay network built by selected mesh routers. We show how a geocast communication mechanism that allows to send messages to all hosts within a specific location can be implemented with this routing algorithm. In extensive evaluations we show that a low proactive routing overhead allows to achieve high message delivery rates even in case of mobility. Moreover, we show that the paths achieved are only 25% longer than the theoretic optimal paths for a wide range of simulation settings.

Application areas like global sensor networks and data stream processing involve the on-line processing of large amounts of data in an overlay network of operators on top of the Internet infrastructure. Trying to fulfill QoS guarantees in such networks is a challenging task that should be realized under the requirement for optimal usage of common resources in the network. Therefore in this paper, we formalize a constrained optimization problem for the placement of operators in an overlay network which strives for satisfying user QoS constraints subject to latency, while minimizing the network load induced by the deployment of the operators in the network. Since the initial problem is NP-hard, we solve at a first step the problem in an intermediate continuous latency space and then we map the continuous solution to its discrete variant. Our evaluations provide an analysis about the inherent interdepedence between the two metrics, network usage and latency, subject to this paper and furthermore show that our algorithm achieves a good balance between the user requirements and the usage of the network resources.

Processing streams of data in an overlay network of operators distributed over a wide-area network is a common idea shared by different applications such as distributed event correlation systems and large-scale sensor networks. In order to utilize network resources efficiently and allow for the parallel deployment of a large number of large-scale operator networks, suitable placement algorithms are vital that place operators on physical nodes. In this paper, we present a distributed placement algorithm that minimizes the bandwidth-delay product of data streams between operators of the network in order to reduce the induced network load. Since the fundamental optimization problem is NP-hard, we propose a heuristic solution. First, we calculate an optimal solution in an intermediate continuous search space, called latency space. Subsequently the continuous solution is mapped to the physical network. Our evaluations show that this algorithm reduces the resulting network load significantly compared to state of the art algorithms and achieves results close to the optimum.

Scaling heterogeneous information systems (HIS) to thousands of sources poses particular challenges to source discovery. It requires a powerful formalism for describing the contents of the sources in a concise manner and for formulating compatible queries as well as a suitable structure for indexing and retrieving the source descriptions efficiently.

Distributed Hash Table (DHT)-based peer-to-peer information discovery systems have emerged as highly scalable systems for information storage and discovery in massively distributed networks. Originally DHTs supported only point queries. However, recently they have been extended to support more complex queries, such as multiattribute range (MAR) queries. Generally, the support for MAR queries over DHTs has been provided either by creating an individual index for each data attribute or by creating a single index using the combination of all data attributes. In contrast to these approaches, we propose to create and modify indices using the attribute combinations that dynamically appear in MAR queries in the system. In this paper, we present an adaptive information discovery system that adapts the set of indices according to the dynamic set of MAR queries in the system. The main contribution of this paper is a four-phase index adaptation process. Our evaluations show that the adaptive information discovery system continuously optimizes the overall system performance for MAR queries. Moreover, compared to a non-adaptive system, our system achieves several orders of magnitude improved performance.

Peer-to-peer (P2P) networks allow for efficient information discovery in large-scale distributed systems. Although point queries are well supported by current P2P systems - in particular systems based on distributed hash tables (DHTs) -, providing efficient support for more complex queries remains a challenge. Our research focuses on the efficient support for multiattribute range (MAR) queries over DHT-based information discovery systems. Traditionally, the support for MAR queries over DHTs has been provided either by creating an individual index for each data attribute or by creating a single index using the combination of all data attributes. In contrast to these approaches, we propose to create a set of indices over selected attribute combinations. In order to limit the overhead induced by index maintenance, the total number of created indices has to be limited. Thus, the resulting problem is to create a limited number of indices such that the overall system performance is optimal for MAR queries. In this paper, we propose an index recommendation tool that implements heuristic solutions to this NP-hard problem. Our evaluations show that these heuristics lead to a close-to-optimal system performance for MAR queries.

In this paper we introduce mechanisms for automated mapping of urban areas that provide a virtual sensor abstraction to the applications. We envision a participatory system that exploits widely available devices as mobile phones to cooperatively read environmental conditions as air quality or noise pollution, and map these measurements to stationary virtual sensors. We propose spatial and temporal coverage metrics for measuring the quality of acquired sensor data that reflect the conditions of urban areas and the uncontrolled movement of nodes. To achieve quality requirements and efficiency in terms of energy consumption, this paper presents two algorithms for coordinating sensing. The first is based on a central control instance, which assigns sensing tasks to mobile nodes based on movement predictions. The second algorithm is based on coordination of mobile nodes in an ad-hoc network. By extensive simulations, we show that these algorithms achieve a high quality of readings, which is about 95% of the maximum possible. Moreover, the algorithms achieve a very high energy efficiency allowing for drastic savings compared to uncoordinated sensing.

The dissemination of messages according to clients' contexts (i.e., location and other attributes) opens up new possibilities in context-aware systems. While geocast or content-based publish/subscribe forward messages according to client location or attributes, respectively, neither uses a combination of the two. In this paper, we present this new communication paradigm and the challenges it poses. We also extend concepts from publish/subscribe networks to efficiently deal with highly dynamic user location to lower update rates by approximating the user's location. This reduces update rates by between 25% and 90%, depending on the granularity of the approximation.

In this paper we introduce a novel scenario for environmental sensing based on the combination of simple and cheap RFID-based sensors and mobile devices like mobile phones with integrated RFID readers. We envision a system that exploits the availability of these devices to cooperatively read sensors installed in the environment, and transmit the data to a server infrastructure. To achieve quality requirements and efficiency in terms of communication cost and energy consumption, this paper presents several algorithms for coordinating update operations. First, mobile nodes form an ad-hoc network for the cooperative management of requested update times to meet the desired update interval and to avoid redundant sensor reading and collisions during read operations. Second, besides this decentralized coordination algorithm, we also show a complementary algorithm that exploits infrastructure based coordination. By extensive simulations we show that our algorithms allow for autonomous operation and achieve a high quality of sensor updates where nearly 100% of the possible updates are performed. Moreover, the algorithms achieve a very high energy efficiency allowing for several hundred hours of operation assuming a typical battery of a mobile phone.

Mobile clients in context-aware systems benefit from the indirect addressing of users via their context (contextcast), such as addressing messages to all users in downtown Toronto whose age is below 35. There is, however, almost no support for a temporal decoupling in such a contextcast system, i.e.

Moving objects databases (MODs) have been proposed for managing trajectory data, an important kind of information for pervasive applications. To save storage capacity, a MOD generally stores simplified trajectories only. A simplified trajectory approximates the actual trajectory of the mobile object according to a certain accuracy bound. In order to minimize the costs of communicating position information between mobile object and MOD, the trajectory simplification should be performed by the mobile object. To assure that the MOD always has a valid simplified trajectory of the remote object, we propose the generic remote trajectory simplification protocol (GRTS) allowing for computing and managing a simplified trajectory in such a system in real-time. We show how to combine GRTS with existing line simplification algorithms for computing the simplified trajectory and analyze trade-offs between the different algorithms. Our evaluations show that GRTS outperforms the two existing approaches by a factor of two and more in terms of reduction efficiency. Moreover, on average, the reduction efficiency of GRTS is only 12% worse compared to optimal offline simplification.

In this paper, we propose an overlay network supporting world-wide geographic messaging. Our approach is based on hierarchical symbolic coordinates like /usa/fl/miami/. Although hierarchical network topologies lend themselves to the implementation of such overlay networks, they may lead to bottlenecks at the root of the hierarchy, long message paths, and inefficient bandwidth utilization. To avoid these problems, we propose an overlay network that adapts its structure to the users' communication patterns by dynamically adding "shortcut" links to the hierarchy leading to a routing mesh. We present an algorithm that carefully selects shortcuts based on their utility to assure short message paths on the one hand and to reduce the induced overhead on the other hand. Through simulations we show that this approach decreases the average path length significantly and reduces network load to about 50% compared to hierarchical routing.

Space-partitioned Moving Objects Databases (SP-MODs) allow for the scalable, distributed management of large sets of mobile objects' trajectories by partitioning the trajectory data to a network of database servers.

In this paper, we present the system design and evaluation of a Space Filling Curve (SFC)-based P2P information discovery system OID. The OID system uses multiple SFCs to significantly optimize the performance of multi-attribute range queries, particularly for applications with a large number of data attributes where a single big SFC-based index is inefficient. The basic idea is to have multiple SFC based indices and select the best one to perform a query. We also introduce two tree-based query optimizations that increase the scalability of the system.

Moving objects databases (MODs) store objects’ trajectories by spatiotemporal polylines that approximate the actual movements given by sequences of sensed positions. Determining such a polyline with as few vertices as possible under the constraint that it does not deviate by more than a certain accu

Geocast, which allows for forwarding messages to hosts residing at specified geographic areas, is a promising communication paradigm with a wide range of applications. Geocast target areas can be specified either by geometric figures or symbolic addresses, such as /usa/f 1/miami/market-street. In this paper, we present a novel geocast routing protocol for symbolically addressed messages. Compared to geocast protocols based on geometric information, our protocol can operate on simple symbolic location models, and message forwarding does not require costly geometric operations. The proposed protocol is based on an overlay network that is mapped to an IP-based network infrastructure. The overlay network is structured in a hierarchical fashion, to ensure a scalable global geocast service supporting also large target areas. Although our protocol does not rely on a layer 3 multicast protocol, we also show how to improve the performance of message forwarding by integrating a light-weight layer 3 multicast protocol. Our evaluations of the protocol underline the scalability of our approach and show good routing quality leading to short message paths. I.

Geocast is used to send messages to all hosts located in a geographic area. This target area can be defined either by geometric figures like polygons or by symbolic addresses like city names or room numbers. Geographic routing algorithms, which forward messages based on geographic information, can be used to forward geocast messages. If routing of symbolically addressed messages is based on geometric coordinates, complex mappings between symbolic addresses and their geometric extent as well as complex geometric operations are required. Therefore, we propose a routing algorithm for symbolically addressed geocast messages that operates directly on a symbolic location model. This approach does not require any geometric information for message forwarding, and forwarding decisions can be realized efficiently by comparably simple operations.