2017 ASHRAE Annual Conference

In California there are 70 non-residential and apartment house ZNE projects in 2015, whereas there are 21 ZNE projects in Japan in 2015. Hence, it’s supposed to be a good example for ZNE dissemination in Japan to clarify the problems toward ZNE dissemination in California. This paper addresses the energy performance of a ZNE office building in Northern California from the perspectives of simulation, measurement, verification, and code compliance. Simulations of the building’s energy use were undertaken during the design stage to demonstrate code compliance and measurements of actual energy use were taken for six months after occupancy.

Occupancy plays a significant role in the amount of energy used in buildings and their presence is stochastic in nature. There is extensive evidence to suggest that buildings usually do not perform as well as predicted by energy simulation. Use of unrealistic occupancy data as an input of building energy modelling (BEM) is a major reason behind it. As a result, large discrepancies are being observed between predicted and actual energy performance, typically averaging around 30% and reaching as high as 100% in some cases. This paper covers research that aims to develop an occupancy prediction model using Artificial Neural Network (ANN) for improving the accuracy of building energy simulation.

The increase in the electricity bills and the new opportunities to participate in the electricity market has encouraged companies with activities not related to the energy industry to engage and actively participate in the electricity market to reduce costs and become more competitive. With the overarching goal of making cost-effective investments and decarbonizing their operation, the first step to improve these companies’ bottom line is to comprehend their electricity costs. This paper focuses on detailing a methodology to model electricity commercial bills and generate real-time price curves; thus allowing customers to calculate their half-hourly true cost of electricity and to assess the challenges of reaching net zero energy buildings for different UK regions and connection voltage levels, across every month up to the financial year 2019-20.

An accurate building energy forecasting model is the key for real-time control of advanced building energy system and building-to-grid integration. Feature selection, the process of selecting a subset of relevant features, is an essential procedure in data-driven modeling due to its ability to reduce model complexity, increase model interpretability, and enhance model generalization. In building energy modeling research, features are often selected purely based on domain knowledge. There lacks a comprehensive methodology to guide the feature selection process when developing building energy forecasting models. In this research, a systematic feature selection procedure for developing building energy forecasting models is proposed in consideration of statistical data analysis, building physics and engineering practices. The procedure includes three main steps: (Step 1) rule-based feature pre-selection process based on domain knowledge. (Step 2) feature removal process through filter methods to remove irrelevant and redundant variables. And (Step 3) Using wrapper method to obtain the best combinations of features. A case study is presented here using simulated building energy data that are generated from a medium sized commercial building (a DOE reference building). In this study, the energy forecasting model generated by using the proposed systematic feature selection process is compared with other models such as a model that uses conventional inputs, and a model with single feature selection technique. The comparison result shows that, in terms of cross validation error, the model with systematic feature selection process shows much better model performance than other models including that with conventional inputs and that uses only single feature selection technique.