High-fidelity modeling is an essential design tool for many engineering applications. However, for complex systems, computational cost can be a limiting factor. Analyzing parameter sensitivity, uncertainty quantification, and design optimization require many model evaluations. Surrogate models are often used to develop the relationship between model parameters and quantities of interest. However, in the case of complex systems, surrogate models require several degrees of freedom and, thus, a large number of data points to determine the correct dependencies. For many applications, this may be prohibitively expensive. The reduction of computational requirements can be achieved by leveraging low-fidelity models. Low-fidelity models represent the system at a coarser resolution with the advantage of computational efficiency. Therefore, a bi-fidelity modeling paradigm, which augments the accuracy of a low-fidelity model in a computationally efficient manner by invoking limited runs of a high-fidelity model, can be leveraged to sufficiently balance the accuracy and computational requirements. In this work, a bi-fidelity weighted transfer learning method using neural networks was applied to a computational fluid dynamics heat transfer modeling problem. The transfer learning advantage was investigated as a function of hyperparameters. Our main finding is that the use of a bi-fidelity modeling paradigm achieves accuracy close to that of a high-fidelity Gaussian process model while significantly reducing computational cost. The bi-fidelity model achieves comparable performance with 90 high-fidelity samples-that is, 60% less than the samples needed to achieve similar accuracy without the use of bi-fidelity modeling,

The buildings sector is one of the largest energy consuming entities today, accounting for about 40% of global energy consumption. Alongside, electricity prices are increasing in several nations worldwide, putting pressure on facility managers to reduce the expense incurred in operating their buildings. In this paper, we focus on building heating, ventilation, and air conditioning and make the following contributions. First, inspired by the deployment of Internet of Things in buildings, we propose a data driven gray box model for zone thermal dynamics and use it to develop an optimization framework for precooling a building. The goal is to determine a precooling strategy that not only shifts the peak air conditioning power to low electricity tariff regimes, but also reduces the peak power, energy consumption, and electricity costs associated with cooling a building. Second, the optimal precooling problem turns out to be nonlinear. To enable ease of use of our framework in the real-world without undermining its efficacy, we develop a linearized version of the problem and show that it has comparable performance to the original formulation. Third, we quantify the benefits of the precooling optimization framework by applying it to building management system data, across multiple days, obtained from a large office building in Australia. The evaluations reveal that optimal precooling lowers the peak power, energy consumption, and electricity costs for cooling the building by up to 30% while ensuring that the thermal comfort of the occupants is maintained. We conclude by describing two applications of the proposed optimization framework for use in developing countries. Our precooling solution incurs no capital expense and permits facility managers to take decisions from a data driven point of view for improving the energy efficiency of their buildings.

Buildings consume almost 40\% of energy in the US. In order to optimize the operation of buildings, models that describe the relationship between energy consumption and control knobs such as set-points with high predictive capability are required. Data driven modeling techniques have been investigated to a somewhat limited extent for optimizing the operation and control of buildings. In this context, deep learning techniques such as Recurrent Neural Networks (RNNs) hold promise, empowered by advanced computational capabilities and big data opportunities. This paper investigates the use of deep learning for modeling the power consumption of building heating, ventilation and air-conditioning (HVAC) systems. A preliminary analysis of the performance of the methodology for different architectures is conducted. Results show that the proposed methodology outperforms other data driven modeling techniques significantly.

Residential buildings account for a significant proportion of overall energy consumption across the world. Decentralized room level Air Conditioners (ACs) are a commonplace in developing countries such as India, contributing a major share (34% in India) of the total residential energy consumption. Option to independently control each AC presents a prime opportunity for an energy saving system. Thus, we propose PACMAN to non-intrusively (using only the temperature information) predict AC energy consumption prior to usage and estimate energy consumption post-usage. We discuss various possible applications and use cases of such feedback for the occupants. To empirically validate the performance of PACMAN, we conducted an in-situ study across seven homes in Delhi (India). We collected around 2200 hours of usage data from the different ACs, room types, and thermostat temperatures. We achieved an average accuracy of 85.3% and 83.7% with the best accuracy of 97.0% and 93.3% for the estimation and prediction of AC energy consumption respectively, across all homes. Towards the end, we discuss various outlier scenarios, opening up multiple directions for further research in this domain.