No abstract

No abstract

No abstract

A Nearly Zero Energy Home (NZEH) in Strathroy, Ontario, Canada was monitored and studied to evaluate its performance for both heating and cooling seasons. The house is a new built and is equipped with an electric-natural gas hybrid spacing heating system. A high efficiency natural gas furnace and an electric air source heat pump (ASHP) were coupled to meet the space heating demand of the house. The house also benefits from on-site renewable energy generation (solar PV). The original system was controlled by a simple switch over thermostat that drives furnace or ASHP based on the outdoor temperature as a single decision-making factor. The system then was upgraded with a cloud based Smart Dual Fuel Switching System (SDFSS) controller that considers time-of-use (TOU) pricing, fuel cost, weather forecast, and equipment efficiencies and capacities. This multi-variable decision-making process defines an optimal schedule for the hybrid system to run more efficiently and more economically. A detailed monitoring system, including sensors, meters, and data acquisition system, was installed to collect all required information at a 2-minute interval. The furnace and ASHP were studied separately to verify their capacities and efficiencies. Then the overall hybrid system and its controller were monitored to identify its effectiveness. A complete model of the house and the hybrid system were developed and validated with experimental data. Thereafter, the system was run by the SDFSS controller. All of these scenarios were compared against each other and benchmarked. In addition, the factors affect indoor air quality (IAQ) were studied in detail. The preliminary result has shown that SDFSS controller provides a cost effective, feasible, cleaner and healthier IAQ options to run the hybrid system in a NZEH.

Machine learning algorithms using Artificial Neural Network (ANN) were developed to predict the performance of heat pump systems in retrofit residential housing. The study attempts to address the research gap in the application of machine learning algorithms to real-life field measurements as a case study. Rowhouse units with electric resistance baseboard heating were retrofitted with Ductless Air Source Heat Pumps (DASHPs). Sensors were installed to collect the energy consumption data during the baseboard and DASHP monitoring periods. Linear and quadratic regression methods following the International Performance Measurement and Verification Protocol (IPMVP) were applied to predict energy consumption based on outdoor temperature and heating degree days. These predictions were compared against results from ANN models based on Levenberg-Marquardt algorithms using the hour of the day, day of the week, outdoor temperature, wind speed and direction, relative humidity, condition and indoor temperature as inputs. Preliminary results indicate that predictions from ANN models produced higher correlation of determination than those from IPMVP regression analysis.