AI-based mission-critical software exposes a blessing and a curse: its inherent statistical nature allows for flexibility in result quality, yet the mission-critical importance demands adherence to stringent constraints such as execution deadlines. This creates a space for trade-offs between the Quality of Result (QoR)-a metric that quantifies the quality of a computational outcome-and other application attributes like execution time and energy, particularly in real-time scenarios. Fluctuating resource constraints, such as data transfer to a remote server over unstable network connections, are prevalent in mobile and edge computing environments-encompassing use cases like Vehicle-to-Everything, drone swarms, or social-VR scenarios. We introduce a novel approach that enables software engineers to easily specify alternative AI service chains-sequences of AI services encapsulated in microservices aiming to achieve a predefined goal-with varying QoR and resource requirements. Our methodology facilitates dynamic optimization at runtime, which is automatically driven by the MARQ framework. Our evaluations show that MARQ can be used effectively for the dynamic selection of AI service chains in real-time while maintaining the required application constraints of mission-critical AI software. Notably, our approach achieves a 100x acceleration in service chain selection and an average 10% improvement in QoR compared to existing methods.

Time-critical requests are becoming increasingly important for microservice service chains. For such service chains, a late response may be worthless or cause failures. Previous works proposed to prevent late responses by trading computation time for result quality, depending on the available resources. However, determining the Quality of Result (QoR) for each operation in a service chain ahead of time, as is the state of the art, cannot prevent requests that are currently processing from being late if resource availability changes, e.g., due to resource sharing at inelastic Edge sites. Therefore, we present a framework to control the QoR online by replanning QoR values whenever resource changes are detected.

The proximity of Mobile Edge Computing offers the potential for offloading low latency closed-loop applications from mobile devices. However, to repair decreases in quality of service (QoS), e.g., resulting from user mobility, the placement of service instances must be continually updated - essential for mission critical applications that cannot tolerate decreased QoS, for example virtual reality or networked control systems. This paper presents BigMEC, a decentralized service placement algorithm that achieves scalable, fast, and high-quality placements by making local service migration decisions immediately when a drop in QoS is detected. The algorithm relies on reinforcement learning to adapt to unknown scenarios and to approximate long-term optimal placement updates by taking future transition costs into account. BigMEC limits each decentralized migration decision to nearby edge sites. Thus, decision computation times are independent of the number of nodes in the network and well below 10ms in our experimental setup. Our ablation study validates that, using its scalable approach to decentralized resource conflict resolution, BigMEC quickly approaches optimal placement with increasing local view size, and that it can reliably learn to approximate long-term optimal migration decisions, given only a black-box optimization objective.

Learning a musical instrument requires regular exercise. However, students are often on their own during their practice sessions due to the limited time with their teachers, which increases the likelihood of mislearning playing techniques. To address this issue, we present Let’s Frets - a modular guitar learning system that provides visual indicators and capturing of finger positions on a 3D-printed capacitive guitar fretboard. We based the design of Let’s Frets on requirements collected through in-depth interviews with professional guitarists and teachers. In a user study (N=24), we evaluated the feedback modules of Let’s Frets against fretboard charts. Our results show that visual indicators require the least time to realize new finger positions while a combination of visual indicators and position capturing yielded the highest playing accuracy. We conclude how Let’s Frets enables independent practice sessions that can be translated to other musical instruments.

Fog Computing extends Cloud Computing by placing resources in the core network between cloud resources and (mobile) users. While a lot of frameworks to implement Fog Computing have been proposed, most do not consider loose coupling between federated fog resources. In such environments, the scalable discovery and orchestration of fog resources across multiple administrative domains and autonomous systems remains a challenge. In this paper, we present Sunstone1, a discovery mechanism for Fog Computing that works on Internet-scale by combining on-path and off-path discovery mechanisms. Leveraging protocols present in the global routing infrastructure, Sunstone operates across multiple fog-domains while requiring no modifications to existing network middleboxes in the transit network. Furthermore, Sunstone includes a customizable orchestrator, which- given the results of the discovery process and application-specific policies-allows for a QoS-aware placement of applications in the fog.

We introduce an assessment framework for edge computing applications. The framework allows developers to measure the execution time of their applications in different environments and generate a model for the prediction of execution times. Based on these measurements and predictions, better informed management decisions can be made for edge applications.