The advent of the Industrial Internet of Things (IIoT), which promotes increasing level of integration between edge devices, commodity computers, and low power sensors to support QoS-sensitive applications, is empowering the next information technology (IT) revolution: city-scale smart cyber-physical systems. Coverage, extensibility and smartness are three pillars of this emerging paradigm. Coverage implies the broad reach as well as the ability to package heterogeneous applications on single or connected platforms. Extensibility implies the flexibility to grow or shrink with respect to the set of services supported by a group of smart applications and hardware resources used to provide these services. Smartness is the capacity of a system to learn and adapt to a changing environment and unplanned circumstances.
Unlike traditional CPS, these systems are multi-domain and operate across conventional organizational and infrastructural boundaries. Further, they operate at multiple time-scales, ranging from automatic control requiring strict real-time decision and actuation, to near real-time operation with humans in the loop, all the way to long term analysis, planning, and decision making, which require large-scale data assimilation, analytics, and mining. Decision support systems that provide critical analysis and feedback to humans play an important role in these systems.
At SCOPE Lab we are conducting research to solve a number of challenges that need to be overcome in order to be able to transition to a scalable architecture that can be used as the foundation for building these extensible smart systems. Given the societal role of these systems, ensuring behavioral correctness across different applications from different domains is very important. Resilient self-management and system scalability are also crucial requirements. The key is to move critical computation near the physical source of information away from a central location, improving the response latency of the system while decreasing the probability and impact of centralized failure. Finally, given the importance of decision support systems, a concerted effort on developing data repositories, analytics and mining packages that can be reused to develop smarter applications is required.
In this project, we use the public transit system in the city of Nashville as a case study to develop tools and techniques for collecting the data, modeling and then analyzing these systems. The outcome of this project will be a smart phone application powered by a real-time decision support system that will enable the transit customers to engage more effectively with the system and allow the Metro transit authority to gain a better insight into several key aspects of the system, allowing them to make it more efficient.
The CHARIOT (Cyber-pHysical Application aRchItecture with Objective-based reconfiguraTion) project, aims to address the challenges stemming from the need to resolve various challenges within extensible CPS found in smart Cities. CHARIOT is an application architecture that enables design, analysis, deployment, and maintenance of extensible CPS by using a novel design-time modeling tool and run-time computation infrastructure. In addition to physical properties, timing properties and resource requirements, CHARIOT also considers heterogeneity and resilience of these systems. The CHARIOT design environment follows a modular objective decomposition approach for developing and managing the system. Each objective is mapped to one or more data workflows implemented by different software components. This function to component association enables us to assess the impact of individual failures on the system objectives. The runtime architecture of CHARIOT provides a universal cyber-physical component model that allows distributed CPS applications to be constructed using software components and hardware devices without being tied down to any specific platform or middleware. It extends the principles of health management, software fault tolerance and goal based design.