Search

• Provided a platform to test various residential building control systems. • Used probability of occupancy to determine setback temperature when unoccupied. • Integrated optimizer with adaptive and occupancy control. • Generated dynamic electricity tariff based on wholesale electricity pricing. • Evaluated the peak load shaving potential with dynamic pricing and optimization. Energy consumption in buildings continues to rise with increased deployment of energy-consuming equipment such as Heating, Ventilation, and Air Conditioning (HVAC) amid a growing world economy. Renewable energy is projected to comprise a majority of the future electricity supply, but the intermittent nature of renewables means that consumption must respond to dynamic supply for optimal utilization. This paper proposes a novel HVAC control strategy for residential buildings using the adaptive comfort model, considering occupancy through probability and real-time information, and optimizing the HVAC schedule to reduce cost, maintain thermal comfort, and respond to the dynamic availability of renewable energy while being generalizable to different situations. To validate this approach, the Universal CPS Environment for Federation (UCEF) co-simulation platform is used to connect advanced building controls with the building energy simulation software EnergyPlus. Simulations are performed for a residential building in Sacramento, CA during a typical summer week. Economic impacts, energy consumption, and thermal comfort are analyzed for traditional, adaptive, and occupancy-based control strategies under demand-based, tiered, and fixed electric tariff systems. Simulation results show that occupancy consideration, adaptive thermal comfort, and optimization can reduce cost by 50.1 %, electricity consumption by 52.9 %, and discomfort by 56.2 % compared to traditional fixed setpoints. The ability of the proposed HVAC control strategy to shift energy consumption away from peak times under a demand-based tariff system is qualitatively analyzed and findings suggest that maximum load-shifting on a grid-scale is attained using occupancy consideration with optimized control and demand-based pricing. For individual residential buildings, similar economic benefits can be gained using the less-complex adaptive HVAC control strategy with existing tiered or simple electric tariff systems. [ABSTRACT FROM AUTHOR]

In recent years, a large number of building energy consumption prediction models, with various intended uses, have been proposed. The majority of these models have either taken a data-driven or a physical modeling approach, with each approach having its own strengths and limitations. Towards leveraging the strengths and reducing the limitations of each approach for improved prediction performance, this paper presents a hybrid machine-learning approach for occupant-behavior-sensitive energy consumption prediction. The proposed approach is composed of three constituent models: (1) a machine-learning model that learns the impact of outdoor weather conditions from simulation-generated data, (2) a machine-learning model that learns the impact of occupant behavior from real data, and (3) an ensemble model that predicts cooling energy consumption based on the outputs of the first two models. The simulation-generated data were created through simulating a set of reference buildings in EnergyPlus. The real data were collected from an office building in Pennsylvania. The proposed hybrid model was validated on an unseen real dataset. It achieved 0.73 kWh RMSE and 9.07% CV in hourly cooling energy consumption prediction, which indicates that the proposed approach is promising. [ABSTRACT FROM AUTHOR]