The next generation of real-time performance-sensitive systems is expected to be more distributed and dynamic. They will have multiple “knobs" that affect performance and resource allocation. Settings of these knobs will need to be jointly and dynamically optimized in the face of a changing workload and resource supply. Centralized approaches, such as Q-RAM, can efficiently maximize global util...

This paper presents a distributed model predictive control (DMPC) for indoor thermal comfort that simultaneously optimizes the consumption of a limited shared energy resource. The control objective of each subsystem is to minimize the heating/cooling energy cost while maintaining the indoor temperature and used power inside bounds. In a distributed coordinated environment, the control uses mult...

The computing community is facing several big data challenges due to the unprecedented growth in the volume and variety of data. Many large-scale Internet companies use distributed NoSQL data stores to mitigate these challenges. These NoSQL data-store installations require massive computing infrastructure, which consume significant amount of energy and contribute to operational costs. This cost...

In this paper, we consider the day-ahead operational planning problem of a radial distribution network hosting Distributed Energy Resources (DERs) including rooftop solar and storage-like loads, such as electric vehicles. We present novel decomposition method that is based on centralized AC Optimal Power Flow (AC OPF) interacting iteratively with self-dispatching DER problems adapting to real r...