Service Engineering Analytics for Hybrid Computing Systems
To solve complex problems, today’s computing systems often employ mixed features of compute, data, network and analytics capabilities from diverse types of machines and humans. They consist of not only powerful resources for data management and analytics from clouds, sensing and actuating capabilities from Internet of Things (IoT), but also critical analytics from humans. This creates a new class of computing systems that we (re)define them as hybrid computing systems (HCS). We especially concentrate on HCS consisting of services blending IoT, network function, cloud services, and human capabilities. We expect that such HCS will be designed, developed and deployed at the core of many vital application domains and will be provisioned as utilities under pay-per-use principles. However, if we look at the way we build HCS, we lack important tools to support the design and optimization of these systems. Our goal is to establish foundational service-based models for HCS by considering HCS as virtual service infrastructures and service slices that will be provisioned and engineered on-demand. SEA4HCS aims at building novel solutions that support the study and optimization of HCS through a set of novel instrumentation, monitoring, simulation, and analysis for crucial attributes of HCS, such as performance, reliability, quality of data, and uncertainty. SEA4HCS introduces symbiotic service engineering analytics for HCS. We want to define and identify of HCS attributes and their associated context and structures. We will develop comprehensive instrumentation, monitoring and simulation for gathering information about HCS behaviours and techniques and methods for analyzing HCS service infrastructures.




Instrumentation, Monitoring, Simulation and Measurement


Analytics Models, Techniques and Algorithms


HCS Service Slices


Use cases




IoTCloudSamples, RAHYMS

New Tools

Will be updated

Contact Me

Hong-Linh Truong (, TU Wien