Andrew Ton

Handling Performance Sensitive Native Cloud Applications with Distributed Cloud Computing and SLA Management

Cloud computing has been used as a platform to reduce cost and increase deployment flexibility for traditional enterprise three-tier web, and some video streaming applications. Typically these types of applications have fairly simple and self-understood performance requirements. Fine-grained constraints on the computation, storage, and networking resources are required support mission-critical enterprise use-cases at a reasonable cost. They are spelled out by service level agreements (SLAs) between the application and the cloud platform. Moreover, new distributed cloud platforms allow for additional deployment patterns, supporting more performance sensitive applications. For example, a specific gaming component will benefit being deployed in the proximity of the (mobile) end-user due to low-latency requirements. In this paper, we motivate the need for more complex performance requirement support with two use cases, electric utility metering and control and public safety. We describe an application management tool, called the Abstract Service Manager (ASM), which is designed to allow the expression of performance requirements in the automated deployment of distributed cloud-native applications. Together with a distributed cloud orchestration system, the ASM automatically mitigates the complexity of constructing performance sensitive applications and their deployment on a distributed cloud.

Towards Timely and Efficient Semantic Reasoning for the Networked Society

This paper presents our work in progress on enabling computerized reasoning capability in machine-to-machine communication scenarios for the Networked Society (or Internet of Things). Such reasoning capability is about drawing high-level conclusions on the situation in real time based on raw data streams generated by various sources. There are challenges posed by the dynamic and heterogenous availability of raw data coming from different sources, as well as the stringent time constraints for conclusions to be made. Our goal hence is to make machine-based reasoning processes time-efficient, resource-efficient, and scalable. We present an approach that addresses the challenges by decomposing a reasoning process into two stages: “shallow reasoning” and “deep reasoning”. The former deals with the dynamic and heterogenous availability of raw data from different sources, while the latter executes semantic reasoning with a lightweight workload that has been reduced by the former. We present our prototype implementation of a reasoning system that adopts the proposed approach in a proactive healthcare use case. Performance evaluation is currently ongoing to verify the effectiveness of our approach.