While existing vertical or horizontal scaling mechanisms work well for cloud platforms that serves a large user base with multi-tenant support, they lead to resource over-provisioning and result in much lower resource utilization at the resource-constrained edges. Addressing this challenge, this work presents Oblique Scalability, a novel system design feature that enables an edge system to handle bursty workloads with minimal redundant resources through equivalent functionalities, which fulfill the same application requirements with dissimilar resources. To systematically support Oblique Scalability, we implement equivalent functionalities as container images, and use Knative on top of k3s to dynamically assign resources and workload for each equivalent functionality at runtime. Through a simulation-based case study and experimental-based evaluation on a heterogeneous cluster of edge devices, we first validate the identified problem and then showcase our proposed system can serve more than 30% requests during workload bursts without deploying additional resources. We demonstrate how our design efficiently utilizes edge resources to adeptly handle workload bursts at runtime in edge systems, thereby enhancing their reliability.

To achieve low execution latency, time-sensitive applications, including AR/ VR and autonomous driving, cache data at the edge of the network, close to end users. However, existing edge caches often fail to deliver low latency due to the inefficiency of DNS requests and the physical remoteness of their users. The solution described herein addresses these inefficiencies by presenting a millisecond-level, lightweight caching architecture that operates directly on widely deployed WiFi access points (APs). Specifically, our architecture interposes another level of caching closer to the client and is fine-tuned for APs’s limited cache memory. Our solution (1) features a novel algorithm for managing cache at the AP level; (2) allows the cache query workflow to proceed at full speed; and (3) requires no changes to the application logic. Our evaluation demonstrates that our reference implementation can decrease application-level latency by as much as 76% compared to the existing solutions, without impacting AP core functions. Our caching architecture effectively improves application responsiveness by tapping into existing networking infrastructure, thus offering a powerful and cost-efficient system component for building emerging time-sensitive applications at the edge.

ShakeAlert is an earthquake early warning (EEW) system that detects significant earthquakes so quickly that alerts can reach many people before shaking arrives. The current ShakeAlert system’s tight coupling between physical sensors and data processing modules has made it difficult to expand new sensors, adopt novel networking technology advances, or change the system’s behavior at runtime, thus hindering the system’s extensibility, scalability, and reliability. To address these limitations, this work proposes to expand the existing system design by adding a “digital twin” middleware layer as virtual representations of physical sensor stations, which provides a standardized software interface for running distributed data processing applications and conceals the hardware/software differences in physical sensors. These virtual stations are placed at the edge of the network near physical stations, acting as a middleware layer between sensors and the ShakeAlert system. By incorporating digital twins, we can leverage cutting-edge networking technologies (such as edge/fog computing) to improve scalability, accept trustworthy sensor data from diverse sources to enhance extensibility, and move data processing functions closer to the sensor stations to reduce response time during large earthquakes when network throughput is impacted. Ultimately, this will enhance the reliability of the ShakeAlert system and help keep communities safe during earthquakes.

After more than a decade since the inception of cloud computing, the underlying technologies supporting it have experienced significant advancements and have now matured enough to provide satisfactory QoS for its users. Among these technologies, particular attention has been given to the development of elasticity, which is a prominent feature of cloud computing. However, the most recent comprehensive survey on elasticity technologies was published in 2017 and fails to encompass the latest progress in the field. Additionally, there is a lack of understanding regarding the interplay of different elasticity technologies. These create a knowledge gap between the high-level concept of cloud elasticity and the state-of-the-art technical details relevant to cloud computing users, developers, and researchers. To address this gap, we carefully select 145 influential papers, both classical and recent, on cloud elasticity. We provide a taxonomy to categorize the enabling technologies of cloud elasticity reported in these papers. For each enabling technology, we thoroughly examine its recent advancements and limitations. This work serves as a valuable resource for cloud computing researchers and practitioners, providing them with a comprehensive review of the up-to-date research and development of cloud elasticity. It also provides a good foundation to enable new researchers and practitioners to enter the field and gain an insight into cloud elasticity.