This letter provides a review of fundamental distributed systems and economic Cloud computing principles. These principles are frequently deployed in their respective fields, but their inter-dependencies are often neglected. Given that Cloud Computin
g first and foremost is a new business model, a new model to sell computational resources, the understanding of these concepts is facilitated by treating them in unison. Here, we review some of the most important concepts and how they relate to each other.
The current Cloud infrastructure services (IaaS) market employs a resource-based selling model: customers rent nodes from the provider and pay per-node per-unit-time. This selling model places the burden upon customers to predict their job resource r
equirements and durations. Inaccurate prediction by customers can result in over-provisioning of resources, or under-provisioning and poor job performance. Thanks to improved resource virtualization and multi-tenant performance isolation, as well as common frameworks for batch jobs, such as MapReduce, Cloud providers can predict job completion times more accurately. We offer a new definition of QoS-levels in terms of job completion times and we present a new QoS-based selling mechanism for batch jobs in a multi-tenant OpenStack cluster. Our experiments show that the QoS-based solution yields up to 40% improvement over the revenue of more standard selling mechanisms based on a fixed per-node price across various demand and supply conditions in a 240-VCPU OpenStack cluster.
We present a testbed for exploring novel smart refrigerator interactions, and identify three key adoption-limiting interaction shortcomings of state-of-the-art smart fridges: lack of 1) user experience focus, 2) low-intrusion object recognition and 2
) automatic item position detection. Our testbed system addresses these limitations by a combination of sensors, software filters, architectural components and a RESTful API to track interaction events in real-time, and retrieve current state and historical data to learn patterns and recommend user actions. We evaluate the accuracy and overhead of our system in a realistic interaction flow. The accuracy was measured to 83-88% and the overhead compared to a representative state-of-the-art barcode scanner improved by 27%. We also showcase two applications built on top of our testbed, one for finding expired items and ingredients of dishes; and one to monitor your health. The pattern that these applications have in common is that they cast the interaction as an item-recommendation problem triggered when the user takes something out. Our testbed could help reveal further user-experience centric interaction patterns and new classes of applications for smart fridges that inherently, by relying on our testbed primitives, mitigate the issues with existing approaches.
In this paper we present the implementation of a WebRTC gateway service that can forward ad-hoc RTP data plane traffic from a browser on one local network to a browser on another local network. The advantage compared to the existing IETF STUN (RFC 53
89), TURN (RFC 5766) and ICE (RFC 5245) protocols is that it does not require a public host and port mapping for each participating local host, and it works with more restrictive firewall policies. WebRTC implements ICE which combines STUN and TURN probes to automatically find the best connection between two peers who want to communicate. In corporate networks, simple hole punching and NAT traversal techniques typically do not work, e.g. because of symmetric NATs. Dynamic allocation of ports on an external 3rd party relay service is also typically blocked on restricted hosts. In our use case, doctors at hospitals can only access port 80 through the hospital firewall on external machines, and they need to communicate with patients who are typically behind a NAT in a local WiFi network. VPN solutions only work for staff but not between patients and staff. Our solution solves this problem by redirecting all WebRTC traffic through a gateway service on the local network that has a secure tunnel established with a public gateway. The public gateway redirects traffic from multiple concurrent streams securely between local gateway services that connect to it. The local gateways also communicate with browsers on their local network to mimic a direct browser-to-browser connection without having to change the browser runtime. We have demonstrated that this technique works well within the hospital network and arbitrary patient networks, without the need for any individual host configuration. In our evaluation we show that the latency overhead is 18-20 ms for each concurrent stream added to the same gateway service.
With the increasing popularity of location-based social media applications and devices that automatically tag generated content with locations, large repositories of collaborative geo-referenced data are appearing on-line. Efficiently extracting user
preferences from these data to determine what information to recommend is challenging because of the sheer volume of data as well as the frequency of updates. Traditional recommender systems focus on the interplay between users and items, but ignore contextual parameters such as location. In this paper we take a geospatial approach to determine locational preferences and similarities between users. We propose to capture the geographic context of user preferences for items using a relational graph, through which we are able to derive many new and state-of-the-art recommendation algorithms, including combinations of them, requiring changes only in the definition of the edge weights. Furthermore, we discuss several solutions for cold-start scenarios. Finally, we conduct experiments using two real-world datasets and provide empirical evidence that many of the proposed algorithms outperform existing location-aware recommender algorithms.
We study the predictive power of autoregressive moving average models when forecasting demand in two shared computational networks, PlanetLab and Tycoon. Demand in these networks is very volatile, and predictive techniques to plan usage in advance ca
n improve the performance obtained drastically. Our key finding is that a random walk predictor performs best for one-step-ahead forecasts, whereas ARIMA(1,1,0) and adaptive exponential smoothing models perform better for two and three-step-ahead forecasts. A Monte Carlo bootstrap test is proposed to evaluate the continuous prediction performance of different models with arbitrary confidence and statistical significance levels. Although the prediction results differ between the Tycoon and PlanetLab networks, we observe very similar overall statistical properties, such as volatility dynamics.
