This project is the convergence of two directions, the first being innovations in residual belief propagation. Belief propagation is an algorithm used to compute statistical inferences on graphs called probabilistic graphical models. Applications include stereo image depth estimation, workplace safety, and healthcare patient experience. The second direction is hardware support for priority-ordered algorithms through task-based parallelism. This work implements belief propagation on an FPGA-based speculative parallel accelerator and demonstrates the possibility of increased performance.
About 60% of the energy consumed by homes in North America is for air conditioning. Residential solar energy is now more cost effective; however, solar energy availability and air conditioning needs are mismatched in time, necessitating energy storage. In previous works, storage of energy in thermal air mass of homes has been proposed, and in this work, an artificial-neural-network-based thermostat is proposed. A method to train the model for an average home is demonstrated with an example and is shown to be effective.
DOI: 10.1109/CCECE47787.2020.9255680
Conventional solar power solutions for homes convert solar energy using photovoltaic (PV) panels and then store the energy in batteries. However, batteries are expensive and environmentally unfriendly. Thermal Energy Storage for Homes (TESH) is a solution to mismatched timing of solar energy and home energy demand. By altering the temperature of the air mass in a home to store thermal energy, one can avoid the need for other forms of energy storage. This makes solar energy an even more environmentally friendly alternative energy source, while simultaneously reducing the cost of infrastructure. The proposed method was implemented as a prototype and tested. Test results are reported and discussed.
DOI: 10.1109/SEGE.2018.8499511