Livio Dalloro

Managing residential-level EV charging using network-as-automation platform (NAP) technology

The amount of power that can be provided for charging the batteries of the electric vehicles connected to a single neighborhood step-down transformer is constrained by the infrastructure. This paper presents a distributed and collaborative residential-level power grid management application to alleviate the need of costly infrastructure upgrade. The application is designed to be hosted in our in-house developed network-as-automation platform (NAP) technology where most of the control functionalities may be moved onto the networking devices. Moreover, we have adapted a service-oriented software engineering principle to achieve scalability, autonomous, and architecture agnostic properties for the residential-level EV charging. We demonstrate a functional prototype where off-the-shelf networking devices capable to host a Linux Operating system are used to showcase the NAP technology. Furthermore, we developed a web-based user interface that may be accessible from any standard computing device, e.g. iPhone, to monitor the runtime operation of this application.

Pipelining for cyclic control systems

This paper presents a novel pipelining technique designed specifically to improve the execution of cyclic control systems and applications in terms of scan cycle time reduction and/or execution of additional workload. Based on the observation that cyclic control systems are tightly coupled with physical processes and that state information (e.g. on/off signals, temperature, pressure) is the most critical data in an application, we present new execution schemes that overlap the execution of multiple cycles in multi-core processors over time. Using an edge detection application benchmark and a software real-time PLC (Programmable Logic Controller) implementation on a quad-core processor, we validate our pipelining method and show the performance scalability of the various schemes. Additionally, we analyze the resilience of our pipelining approach to time delays and propose a speculative execution method to deal with data dependency violations.