Team: Dr. Beryl Chen, Dr. Ludwig Dierks
Overview
This project develops IoT-enabled monitoring and optimization of energy usage in commercial and residential buildings. Buildings account for roughly 40% of total energy consumption in the U.S. - intelligent building systems can significantly reduce this footprint while improving occupant comfort.
Approach
We deploy sensor networks that capture fine-grained energy, temperature, humidity, and occupancy data. Large-scale convex optimization models then determine optimal HVAC scheduling, lighting control, and demand response strategies. Our preconditioning techniques for first-order methods enable these optimizations to run in near-real-time on edge computing devices within the building.
Impact
Field trials in two commercial office buildings showed 18-24% reductions in HVAC energy consumption with no degradation in occupant comfort scores. The optimization framework is being packaged as an open-source toolkit for building managers.
Related Publications
An adaptive parameter-free and projection-free restarting level set method for constrained convex optimization under the error bound condition
Q. Lin, N. Soheili, R. Ma, and S. Nadarajah
Journal of Machine Learning Research
Doubly randomized fluid approximation
N. Soheili, S. Nadarajah, and S. Rahnama
SIAM Journal on Optimization
Projection and rescaling algorithm for finding the most interior solutions to polyhedral conic systems
J. Peña and N. Soheili
Mathematics of Operations Research
A level-set method for convex optimization with a feasible solution path
Q. Lin, S. Nadarajah, and N. Soheili
SIAM Journal on Optimization